{"id":1484206,"url":"https://alion.io/job/salt-ai-engineer-3","title":"Ai Engineer","company":{"id":1935342,"name":"Salt","domain":"welovesalt.com","url":"https://alion.io/company/welovesalt","size_band":"201-500","is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":{"grade":"C","score":64,"open_postings":1440,"ghost_share":0.608,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-01T05:45:00Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"senior","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Dubai, United Arab Emirates"],"countries":["AE"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":20000,"max":null,"currency":"AED","period":"month","gross":null,"usd_annual":65364},"salary_estimate":null,"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Airflow","optional":false},{"name":"Anthropic","optional":false},{"name":"Azure","optional":false},{"name":"Azure AKS","optional":false},{"name":"CI/CD","optional":false},{"name":"Cohere SDK","optional":false},{"name":"Computer Vision","optional":false},{"name":"FastAPI","optional":false},{"name":"Function Calling","optional":false},{"name":"Git","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"LangChain","optional":false},{"name":"LangGraph","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"Machine Learning","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Node JS","optional":false},{"name":"OCR","optional":false},{"name":"OpenAI","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Pydantic","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Rest API","optional":false},{"name":"Structured Outputs","optional":false},{"name":"Tool Use","optional":false},{"name":"TypeScript","optional":false},{"name":"JavaScript","optional":true},{"name":"Kubernetes","optional":true}],"status":"live","first_seen_at":"2026-07-13T00:00:00Z","employer_posted_date":"2026-07-13","last_verified_at":"2026-09-29T22:22:26Z","board_verified":true,"closed_at":null,"days_open":80,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":80},"description":"Back to all jobs\nApplications are now closed.\nAi Engineer\nRef: JO-2607-361886\nUnited Arab Emirates, Dubai \n\nData, AI and Machine Learning, Technology \n\nIT \n\n1,000 - 4,999 Employee \n\nAED 20,000.00 - AED 25,000.00 per month \n\nEnvironment:\n\nIn-office \n\nContract Type:\n\nContract \n\nStarts:\n\n2026-11-02 \n\nDuration:\n\n12 Months \n\nStart Date - ASAP\nMy client is a global data, AI, digital transformation, and consulting company that helps organisations use data and technology to improve business performance, customer experience, and decision-making.\nRole Overview: The AI Engineer is the primary builder within the AWA AICoE. You will design, build, and test the LangGraph agent graphs, LLM extraction pipelines, prompt management workflows, and MCP tool integrations that power AWA’s use cases - starting with Intelligent Document Processing (IDP) for cheque clearing and expanding across the bank’s operations. You will work directly with the dual-layer orchestration stack (Orkes Conductor + LangGraph) and Azure AI Foundry to deliver production-grade agentic systems.\nKey Responsibilities:\nAgent graph development: Design and implement LangGraph agent graphs for Supervisor-Worker orchestration, self-reflection, actor-critic, and HITL interrupt patterns using TypedDict state schemas and conditional edge routing.\nLLM extraction pipeline: Build and maintain LLM-based entity extraction pipelines using Azure AI Foundry, implementing structured output enforcement, per-field confidence scoring, and Pydantic output validation against Use Case Manifest schemas.\nPrompt engineering and governance: Author, version, and govern prompts through the AWA Prompt Management System (PMS) using semantic versioning; run prompt sensitivity and correctness testing using the AWA IDP Test Strategy.\nMCP tool integration: Develop and maintain the five core MCP tool servers (query_structured, retrieve_precedents, query_documents, checkpoint_state, observe) and extend them for new use case requirements.\nModel evaluation and testing: Execute Band 1 and Band 2 testing (Model Testing, Prompt Testing, Agent Testing, AI Security Testing, Adversarial Testing) per the AWA IDP Test Strategy; maintain the Golden Dataset and Regression Dataset.\nHITL framework: Implement HITL interrupt() calls at mandatory and dynamic review points in LangGraph graphs; configure Orkes Wait tasks; validate HITL state persistence and checkpoint-based resumption.\nAI guardrail integration: Integrate Azure AI Content Safety, PII detection and tokenisation, prompt injection shielding, and output sanitisation into agent pipelines at the AWA AI Gateway layer.\nCross-field validation rules: Implement business validation rules (amount-words-vs-figures, date validity, MICR format, referential integrity) within LangGraph validation agent nodes.\nRequired Skills and Experience\nTechnical - Essential:\n5+ years Python development - production-grade, not just scripting\nHands-on experience with LangGraph, LangChain, or equivalent agentic AI frameworks\nPractical LLM prompt engineering: structured outputs, few-shot design, output schema enforcement\nFamiliarity with Azure AI Foundry / OpenAI API or equivalent LLM API (Anthropic, Cohere)\nUnderstanding of agent design patterns: ReAct, self-reflection, tool use, HITL\nREST API development and consumption; JSON schema design\nGit version control; CI/CD pipeline awareness\nTechnical - Advantageous:\nExperience with Orkes Conductor, Apache Airflow, or Temporal for workflow orchestration\nAzure AI Document Intelligence or equivalent OCR platform experience\nComputer vision model integration (object detection APIs)\nKnowledge of RAG architectures: chunking, vector indexing, Azure AI Search\nAzure platform familiarity: AKS, ADLS Gen2, Azure ML, Azure Monitor\nPydantic, FastAPI, TypeScript/Node.js\nDomain and Soft Skills:\nGenuine intellectual curiosity about AI systems and their failure modes\nAbility to explain AI behaviour to non-technical Ops and business stakeholders\nStructured problem-solving and debugging approach for non-deterministic AI systems\nBanking domain interest - willingness to deeply understand the business processes being automated\nSalt is acting as an Employment Business in relation to this vacancy.","description_format":"text","description_chars":4224,"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":[],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-09-29T22:01:35Z"}],"liveness":{"score":7,"band":"cold","label":"Long shot","p_open":1,"p_active":0.207,"p_room":0.36,"age_days":80,"expected_fill_days":47,"reasons":["conf:31","agency","stale_co","evergreen","urgency","velocity","win:tail","crowd:brand"],"computed_at":"2026-10-01T05:45:00Z"},"pay":{"stated_usd_annual":65364,"is_top_pay":false},"html_url":"https://alion.io/job/salt-ai-engineer-3","json_url":"https://alion.io/job/salt-ai-engineer-3.json","meta":{"generated_at":"2026-10-01T10:21:12Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":1449,"day_limit":5000,"remaining_today":3551,"minute_limit":60,"resets_at":"2026-10-02T00:00:00Z"}}}