{"id":722464,"url":"https://alion.io/job/gravityglobal-forward-deployed-ai-engineer-2","title":"Forward Deployed AI Engineer","company":{"id":673735,"name":"Gravity Global","domain":"gravityglobal.com","url":"https://alion.io/company/gravityglobal","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Recruitee","truth_index":{"grade":"B","score":84,"open_postings":8,"ghost_share":0,"stale_share":0.625,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-27T05:46:45Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"senior","employment_type":null,"work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"posting_text","remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Kraków, Poland"],"countries":["PL"],"hiring_countries":["PL"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":63000,"max_usd":107000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":46},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"CI/CD","optional":false},{"name":"Function Calling","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"Multi-Agent Systems","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"TypeScript","optional":false},{"name":"Agentic Workflows","optional":true},{"name":"Anthropic","optional":true},{"name":"Apache Kafka","optional":true},{"name":"Arize Phoenix","optional":true},{"name":"AWS","optional":true},{"name":"AWS Bedrock","optional":true},{"name":"Azure","optional":true},{"name":"Braintrust","optional":true},{"name":"Claude","optional":true},{"name":"Claude Code","optional":true},{"name":"Context Engineering","optional":true},{"name":"Databricks","optional":true},{"name":"Embeddings","optional":true},{"name":"FinOps","optional":true},{"name":"GCP","optional":true},{"name":"GDPR","optional":true},{"name":"Git","optional":true},{"name":"HIPAA","optional":true},{"name":"IAM","optional":true},{"name":"LangChain","optional":true},{"name":"Langfuse","optional":true},{"name":"LangGraph","optional":true},{"name":"LangSmith","optional":true},{"name":"LlamaIndex","optional":true},{"name":"LLM","optional":true},{"name":"LLM Evaluation","optional":true},{"name":"Model Context Protocol","optional":true},{"name":"Multimodal AI","optional":true},{"name":"OpenAI Agents SDK","optional":true},{"name":"Semantic Search","optional":true},{"name":"SOC 2","optional":true},{"name":"SQL","optional":true},{"name":"Structured Outputs","optional":true},{"name":"Terraform","optional":true}],"status":"live","first_seen_at":"2026-08-07T07:39:36Z","employer_posted_date":"2026-08-07","last_verified_at":"2026-10-27T19:27:47Z","board_verified":true,"closed_at":null,"days_open":81,"trust":{"level":"ok","repost_count":0,"flags":[],"days_open":80},"description":"gravity9 is a boutique IT consulting company headquartered in the UK with offices in the US, Canada, Poland, and Colombia. Our team has deep experience in engineering, experience design and product management. We enjoy a challenge and pride ourselves on working with our clients on their most complex problems, finding elegant and flexible solutions that help them transform their businesses.\nJoin Our Growing Team - Future Opportunities Await!\nWe are excited to share that our company is experiencing significant growth and expansion, and as a result, we're on the lookout for talented individuals to join our team.\nWe want to be upfront about our hiring process. At this moment, we are in the process of securing projects that align with our business goals and objectives. Our intention is to ensure that once we bring new team members on board, they will have a meaningful and impactful role to play from day one. While we might not be able to extend an offer immediately, we are highly interested in considering you for these future projects.\nIf you're open to the idea of potentially joining our team in the future, we encourage you to continue with our interview process. We value your time and effort and believe that getting to know you better will help us make an informed decision.\nOnce you have effectively concluded the entire recruitment procedure, we will retain your profile and reach out to you once a suitable opportunity emerges. Additional interviews will not be necessary at this stage, and we anticipate being able to extend an offer to you promptly.\nWhat does the recruitment process look like?\n1. Recruiter Screen\nIn the first call, our recruiter will learn more about you and your story to check a potential fit for gravity9. This is also an opportunity to ask your questions about the role and company. This step might take around 60 mins.\n2. Tech 1 Interview with our AI Practice Lead\nIn this meeting your potential future teammate will take a deeper dive into your experience and what you could bring to the team.\nThis step will take around 75 mins.\n3. Tech 2 Interview with our software consultants\nIn this meeting your potential future teammate will take a deeper dive into your experience and what you could bring to the team.\nThis step will take around 60 mins.\n4. Final Interview\nYou made it to the very last stage! Here we already strive to cooperate with you and give you an opportunity to meet our leadership team during this informal talk. This step will take around 30 mins.\nThe salary details for the role will be communicated ahead of the first recruitment meeting.\nThank you for considering the opportunity to be a part of our growing journey. We look forward to the possibility of working together and achieving great things.\nRole Description\ngravity9 is expanding its Forward Deployed Engineering team to build production agentic AI systems for enterprise clients, in partnership with leading frontier-model providers. We already support clients from different verticals to have agentic and RAG systems live in production across healthcare, financial services, retail and global logistics.\nAs a Forward Deployed AI Engineer you work embedded in the client's environment, from discovery, through architecture and build, to production and handover. This is end-to-end agent engineering, not proofs of concept and not advisory work. Two flavours of engagement:\nInternal enterprise use cases, such as reconciliation and KYC workflows in financial services, clinical and claims workflows in healthcare, operations and supply-chain workflows in logistics.\n\nProduct- and customer-facing agents, more greenfield, often exploratory, built into the client's own product.\n\nEngagements are typically a team of engineers over a few months, working shoulder-to-shoulder with the client's team including architects, DevOps and QA.\nEmbed with the client. Work hand-in-hand inside the client's environment, codebase and cloud tenancy, often in a hybrid team alongside their engineers. You are visible to the client from day one.\n\nDesign and build production agentic AI systems. Multi-agent orchestration, tool and function calling, retrieval, planning and routing, human-in-the-loop checkpoints, state and checkpointing, guardrails, failure handling and recovery.\n\nDo the unglamorous data work. A large share of every engagement is data engineering: ingestion, flattening deeply nested structures, extracting content from unstructured documents, classification, summarisation, tagging, enrichment, indexing. Models reason over data, bad data beats a good model every time.\n\nOwn evaluation and accuracy. Establish a baseline eval dataset at the start of the engagement, automate grading, and track groundedness, faithfulness and retrieval quality per tool, not just at the agent level. Be ready to defend accuracy numbers to a sceptical enterprise stakeholder.\n\nEngineer for cost and latency. Model selection and routing (cheaper, faster models for non-reasoning steps; frontier models where reasoning genuinely earns it), prompt and context budgeting, caching. Cost is a non-negotiable metric on every engagement.\n\nShip it properly. Observability and tracing, CI/CD, IaC, monitoring the client can actually operate, security and compliance review.\n\nTransfer knowledge deliberately. We don't run a long-term support business. Every engagement is designed so the client owns and can extend the system after we leave. You architect with their team in the room, pair with their engineers, and hand over working monitoring and documentation.\n\nRequirements\nTechnical skills\nEssential\nProgramming: Strong Python (async, typing, testing, packaging). Working competence in TypeScript / Node is a plus.\n\nLLM application engineering: Hands-on production experience with frontier models: prompt and context engineering, structured outputs, tool and function calling, streaming, token and context-window management.\n\nAgentic architecture: Built and shipped multi-agent or agentic workflows, planner/router patterns, supervisor and sub-agent designs, ReAct-style loops, state and checkpointing, retries and interrupts, human-in-the-loop review gates.\n\nFrameworks: At least one of: Anthropic Agent SDK, LangGraph, LlamaIndex, or an equivalent orchestration framework, plus the judgement to know when to use none of them.\n\nRAG and retrieval: Chunking strategy, embeddings, hybrid and semantic search, re-ranking, citation and provenance, natural-language-to-query translation.\n\nData platforms: NoSQL databases such as MongoDB (aggregation pipelines, Atlas Search, Atlas Vector Search) or a strong equivalent, plus SQL. Comfortable designing schemas for agent retrieval, not just for OLTP.\n\nData engineering: Building ingestion and enrichment pipelines over messy structured and unstructured sources, documents, PDFs, object storage.\n\nEvaluation: Building eval harnesses and eval datasets, LLM-as-judge with its limits understood, regression testing of prompts and agents, metric selection per use case.\n\nCloud: Production delivery on AWS (incl. Bedrock), Azure or GCP, containers, serverless, networking basics, secrets management, IAM.\n\nEngineering discipline: Git, code review, testing, CI/CD, IaC (Terraform or equivalent), observability.\n\nStrong advantage\nAnthropic certification (Claude Developer / Anthropic-issued credential), an explicit advantage at shortlisting.\n\nAnthropic Agent SDK production experience, a significant bonus.\n\nMCP (Model Context Protocol): building servers and clients, tool exposure, auth patterns.\n\nClaude Code as an autonomous SDLC agent: sub-agents, hooks, custom skills, agent marketplaces, context sharing across a team.\n\nLLM observability and tracing tooling (LangFuse, LangSmith, Arize, Braintrust or similar).\n\nRegulated-environment delivery: HIPAA, GDPR, SOC 2, FCA/PRA, PII handling, data residency, guardrails and red-teaming.\n\nGraph or taxonomy-based knowledge representation alongside vector retrieval.\n\nKafka / streaming, Databricks, or comparable large-scale data platform experience.\n\nNice to have\nVoice and multimodal agents; evaluation of non-text outputs.\n\nFinOps for AI workloads; unit-economics modelling for agent systems.\n\nOpen-source contribution to the agent / LLM ecosystem, or conference speaking.\n\nPrior experience as an FDE, solutions architect, or delivery consultant at a frontier-model, data platform, or infrastructure vendor.\n\nSoft skills\nAn FDE is an engineer who is safe in front of a client. We screen as hard on this section as on the technical one.\nClient presence and credibility. Can hold a technical conversation with a client architect and a business conversation with their CTO or head of operations in the same hour, and be trusted by both. Can present, whiteboard, and answer hard questions without deflecting.\n\nTranslation. Turns a business problem described by non-technical people such as a clinician, campaign manager or supply-chain planner into a technical design, and explains the technical design back in their language.\n\nEgo-free collaboration in a supporting role. On some engagements the tech lead will come from the client or a partner, not from us. You need to contribute strongly, disagree well, and take direction without friction. Brilliant-but-territorial doesn't work here.\n\nComfort with ambiguity and greenfield. Engagements often start before the requirements, the data access, or sometimes the problem statement are settled. You make progress anyway, and you make the ambiguity visible rather than hiding it.\n\nBias to production. Instinctively asks \"how does this get deployed, monitored and maintained?\" rather than stopping at a working notebook.\n\nTeaching instinct. Actively enjoys upskilling the client's engineers, because self-sufficiency at handover is the definition of success, not follow-on billing.\n\nOwnership and pace. Short engagements, small teams, no layers to hide behind. You unblock yourself, chase the access request, and follow the thread to the answer.\n\nCommercial awareness. Understands that scope, cost and the client's willingness to pay are part of the engineering problem, and contributes to scoping and estimating honestly.\n\nResilience and adaptability. New client, new domain, new stack every few months; occasional travel; occasionally a sceptical stakeholder who has been told AI is coming for their job. You stay steady and constructive.\n\nWritten communication. Clear design docs, decision records, handover material and status updates in English. Much of this is asynchronous and cross-timezone.\n\nGenuine curiosity about the field. This ecosystem changes monthly. We want people who are already reading, building side projects and forming opinions - not waiting for training to be scheduled for them.\n\nWhile this is a fully remote position, physical residence in Poland is required.\nExperience profile\nFDE (mid): 3+ years software engineering, 1+ years hands-on LLM / agentic work with at least one system live in production. Client-facing exposure.\n\nSenior FDE: 5+ years engineering, 2+ years AI or agentic AI, has owned the architecture of at least one production agent system end-to-end and led a client conversation about it.\n\nLead FDE: 7+ years, has led delivery teams of 3-7 people, can act as engagement tech lead, contributes to pre-sales and estimation, and can mentor a growing FDE bench.\n\nWhat success looks like\nFirst 90 days - owning a meaningful component of a client-facing agent system, including its evals, and trusted in front of the client.\n\n6 months - designing agent architectures independently, leading a workstream, and running the handover and knowledge-transfer track.\n\n12 months - a reference point for others on the team, contributing to reusable assets, pre-sales and interviewing.\n\nWhat we offer\nSupport for vendor certifications and access to partner training programmes.\n\nCompany-wide AI tooling as part of how we work day to day.","description_format":"text","description_chars":11899,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"Poland","iso":"PL","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Creative Agencies","Digital Marketing"],"lifecycle":[{"event":"open","at":"2026-09-11T07:27:01Z"}],"visa":[],"liveness":{"score":13,"band":"cold","label":"Long shot","p_open":1,"p_active":0.479,"p_room":0.28,"age_days":80,"expected_fill_days":30,"reasons":["conf:4","win:tail","crowd:"],"computed_at":"2026-10-27T05:46:45Z"},"pay":null,"html_url":"https://alion.io/job/gravityglobal-forward-deployed-ai-engineer-2","json_url":"https://alion.io/job/gravityglobal-forward-deployed-ai-engineer-2.json","meta":{"generated_at":"2026-10-27T23:21:30Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":15320,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-28T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":673735},"rest":"https://alion.io/mcp/rest/get_company?id=673735"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fgravityglobal-forward-deployed-ai-engineer-2"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fgravityglobal-forward-deployed-ai-engineer-2"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fgravityglobal-forward-deployed-ai-engineer-2"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/gravityglobal-forward-deployed-ai-engineer-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fgravityglobal-forward-deployed-ai-engineer-2"}]}