{"id":3266693,"url":"https://alion.io/job/onit-ai-engineer","title":"AI Engineer","company":{"id":58716,"name":"Onit","domain":"onit.com","url":"https://alion.io/company/onit","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Lever","truth_index":{"grade":"A","score":86,"open_postings":4,"ghost_share":0,"stale_share":0.75,"repost_share":0,"time_to_fill_p50_days":19,"computed_at":"2026-10-31T05:58:55Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Pune, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Agentic Workflows","optional":false},{"name":"AI Agents","optional":false},{"name":"Anthropic","optional":false},{"name":"Azure","optional":false},{"name":"CI/CD","optional":false},{"name":"Context Engineering","optional":false},{"name":"Function Calling","optional":false},{"name":"Gemini","optional":false},{"name":"Langfuse","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"Multi-Agent Systems","optional":false},{"name":"OpenAI","optional":false},{"name":"OpenTelemetry","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Vertex AI","optional":false},{"name":"AWS","optional":true},{"name":"Braintrust","optional":true},{"name":"Celery","optional":true},{"name":"Datadog","optional":true},{"name":"GCP","optional":true},{"name":"Honeycomb","optional":true},{"name":"Weights & Biases","optional":true}],"status":"live","first_seen_at":"2026-04-13T13:32:33Z","employer_posted_date":"2026-04-13","last_verified_at":"2026-10-31T04:48:12Z","board_verified":true,"closed_at":null,"days_open":200,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":200},"description":"We’re seeking a AI Engineer to design and ship production-grade agentic AI systems that automate complex workflows end-to-end. This is a hands-on role with significant technical ownership. You’ll work closely with the Chief Architect, product, engineering, and domain experts to translate ambiguous, high-impact problems into reliable AI-driven user experiences.\nWhat success looks like:\nShip AI capabilities that measurably improve user outcomes (quality, time saved, throughput)\nBuild systems that are reliable by design: evals, observability, safety, and cost/latency controls from day one\nIterate quickly using a tight loop of instrument → evaluate → improve → deploy\nWhat You’ll Do\nAgentic AI Feature & Workflow Development\nBuild and integrate AI-driven features using LLM APIs (OpenAI / Azure OpenAI, Anthropic, Gemini on Vertex AI)\nDesign and implement tool-using agents (structured function calling, schema validation, retries, fallbacks)\nBuild multi-agent workflows when appropriate (e.g., planner/worker, reviewer/critic, specialist routing) and know when a simpler architecture is better\nCreate agentic workflows such as document understanding, extraction, reasoning over evidence, task automation, and multi-step decision support\nOwn context engineering end-to-end:\ndynamic context assembly (retrieval + state + tool outputs)\ncontext budgeting and compression/summarization\ngrounding strategies to reduce hallucinations and improve consistency\nImplement retrieval-augmented generation (RAG) and search workflows using off-the-shelf vector stores and embedding services \nEvaluation, Quality & Iteration (Core)\nEstablish evaluation frameworks for accuracy, reliability, and output quality\nBuild task-specific eval suites: golden datasets, adversarial cases, regression tests, and rubric-based scoring\nSet up automated evaluation pipelines and release gates (CI/CD-friendly) tied to prompt/model/version changes\nDefine and monitor online metrics (e.g., task success rate, human override rate, safety flags, latency, cost) and run experiments/A-B tests where appropriate\nUse LLM-as-judge responsibly: calibrate, validate, and pair with human labels when needed \nEngineering, Integration & Observability\n\nDevelop scalable backend services and APIs that incorporate AI functionality\nIntegrate AI pipelines into existing cloud, microservices, and event-driven architectures\nImplement observability and analytics for all AI features (tracing, evaluations, prompt versioning, cost tracking) Example tooling: Langfuse (and/or OpenTelemetry-compatible stacks)\nEnsure reliability, uptime, performance, and security of AI services\nBuild internal tooling for evaluation, testing, prompt/version management, and safe deployment\nProduct & Collaboration\nPartner with product managers, designers, the Chief Architect, and domain SMEs to shape AI-first solutions\nRapidly prototype concepts and iterate based on user feedback and measurable eval results\nTranslate business problems into well-structured AI workflows without requiring ML model training\nDocument system behavior, known failure modes, and operational playbooks \nGovernance & Safety\nImplement guardrails, checks, and fallback logic for safe and predictable AI behavior\nHelp define and follow compliance, privacy, and responsible AI guidelines\nDesign for safe tool execution (bounded actions, permissions, escalation paths, human-in the-loop review \nWhat You Bring\nCore Strengths (Required)\nStrong software engineering background (Python preferred) and experience shipping backend services\nDeep hands-on experience building agentic LLM systems from first principles: agent loops, tool interfaces, planning/replanning, memory/state, and failure handling\nStrong context engineering ability: retrieval strategies, routing, grounding, context budgeting, and long-context tradeoffs\nStrong evaluation discipline: golden datasets, regression gating, automated eval pipelines, and online monitoring\nPractical experience with LLM APIs (OpenAI/Azure OpenAI/Anthropic/Gemini) and AI orchestration frameworks\nExcellent debugging, systems thinking, and problem decomposition skills\nComfortable operating in fast-paced, ambiguous environments with high ownership \nSignals We Value\nYou’ve shipped an LLM/agent system in production and can clearly explain:\nthe failure modes you discovered\nthe evals you built to catch regressions\nhow you improved cost/latency while increasing quality\nhow you monitored and iterated safely over time \nYou keep up with industry developments (model releases, frameworks, best practices) and can translate them into pragmatic improvement \nNice to Have\nExperience with cloud platforms (AWS and/or GCP), microservices, and event-driven systems\nExperience with observability stacks (OpenTelemetry, Datadog, Honeycomb) and AI-specific tooling (e.g., Langfuse, Braintrust, HumanLoop, W&B Weave)\nExperience with workflow orchestration for long-running jobs (Temporal, Celery, Airflow)\nExperience building enterprise AI features (permissions, auditability, compliance constraints)\nExperience with safety/policy layers (PII handling, prompt injection defenses, sandboxed tool execution) \nWhy Join Us\nBuild core AI capabilities that directly impact users and product strategy\nWork on cutting-edge, real-world agentic systems-focused on applied engineering (no model training required)\nHigh ownership, fast iteration cycles, and strong cross-functional collaboration\nCompetitive compensation and opportunities for rapid advancement \nWhat Your First 90 Days Could Look Like\nShip one production agent workflow end-to-end with:\ntracing + observability\nan offline eval suite with regression gates\ncost/latency targets and monitoring\ndocumented failure modes and fallback path","description_format":"text","description_chars":5730,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence","Cybersecurity","Document Management","Digital Signature"],"lifecycle":[{"event":"open","at":"2026-10-26T09:35:19Z"}],"visa":[],"liveness":{"score":4,"band":"cold","label":"Long shot","p_open":1,"p_active":0.135,"p_room":0.28,"age_days":200,"expected_fill_days":19,"reasons":["conf:1","velocity","win:tail","crowd:"],"computed_at":"2026-10-31T05:58:55Z"},"pay":null,"html_url":"https://alion.io/job/onit-ai-engineer","json_url":"https://alion.io/job/onit-ai-engineer.json","meta":{"generated_at":"2026-10-31T06:40:51Z","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":9837,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-01T00:00:00Z"}},"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":58716},"rest":"https://alion.io/mcp/rest/get_company?id=58716"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fonit-ai-engineer"},{"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%2Fonit-ai-engineer"},{"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%2Fonit-ai-engineer"},{"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/onit-ai-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fonit-ai-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3266693}},{"tool":"search_jobs","arguments":{"company":"onit.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3266693},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}