{"id":1460718,"url":"https://alion.io/job/ajackus-senior-generative-ai-engineer","title":"Senior Generative AI Engineer","company":{"id":3806660,"name":"AJACKUS","domain":"ajackus.com","url":"https://alion.io/company/ajackus","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"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":["Mumbai, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":19500,"max_usd":41000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":29},"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Agentic Workflows","optional":false},{"name":"AI Agents","optional":false},{"name":"AWS","optional":false},{"name":"Embeddings","optional":false},{"name":"FastAPI","optional":false},{"name":"Function Calling","optional":false},{"name":"Hallucination","optional":false},{"name":"LLM","optional":false},{"name":"pgvector","optional":false},{"name":"PostgreSQL","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Redis","optional":false},{"name":"Tool Use","optional":false},{"name":"WhatsApp","optional":false},{"name":"ISO 27001","optional":true},{"name":"SOC 2","optional":true}],"status":"live","first_seen_at":"2026-09-29T11:31:42Z","employer_posted_date":null,"last_verified_at":"2026-09-29T11:31:42Z","board_verified":false,"closed_at":null,"days_open":2,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":2},"description":"Role Overview : \n\nWe are looking for a Senior Generative AI Engineer to build and own production-grade LLM and agentic AI capabilities for an AI-powered concierge platform. The role will focus on building intelligent agents that can understand user requests, retrieve relevant information, use tools, execute multi-step workflows, and safely take actions on behalf of users.\n\nKey Responsibilities : \n\n- Design and develop production-grade Generative AI and LLM applications using Python.\n\n- Build agentic workflows that support tool calling, multi-step reasoning, confirmation, escalation, and failure recovery.\n\n- Develop AI-powered WhatsApp workflows for bookings, payments, knowledge retrieval, and customer interactions.\n\n- Build and optimize RAG pipelines with tenant-scoped retrieval and grounded responses.\n\n- Integrate LLM APIs for text generation, embeddings, classification, summarization, and intelligent decision-making.\n\n- Design prompts, system instructions, tool definitions, and agent workflows to achieve reliable production outcomes.\n\n- Build evaluation frameworks and golden datasets to measure accuracy, reliability, hallucination, and agent performance.\n\n- Implement safeguards against prompt injection, data leakage, unauthorized actions, and unsafe tool usage.\n\n- Optimize LLM applications through model routing, prompt optimization, caching, batching, and efficient context management.\n\n- Monitor and improve latency, token consumption, quality, and reliability of AI interactions.\n\n- Build tenant-aware AI services ensuring appropriate data isolation and access control.\n\n- Collaborate with backend engineers to define APIs and tool interfaces required by AI agents.\n\n- Develop asynchronous production services using Python and FastAPI.\n\n- Contribute to CI-based AI regression testing, monitoring, and model/drift evaluation.\n\n- Work closely with product and engineering teams to translate user journeys into reliable AI experiences.\n\nRequired Skills : \n\n- 4+ years of production software engineering experience with substantial hands-on experience in Generative AI / LLM systems.\n\n- Strong expertise in Python.\n\n- Hands-on experience building production LLM applications and AI agents.\n\n- Strong experience with RAG, embeddings, vector search, and grounded generation.\n\n- Experience with LLM tool calling and multi-step agentic workflows.\n\n- Experience with LLM evaluation, prompt engineering, and AI quality measurement.\n\n- Strong understanding of AI security, prompt injection, data privacy, and access control.\n\n- Experience building asynchronous production services using FastAPI.\n\n- Experience with PostgreSQL, pgvector, Redis, and AWS.\n\n- Proven experience optimizing LLM latency and token costs while maintaining response quality.\n\nGood to Have : \n\n- Experience with WhatsApp or conversational AI platforms.\n\n- Experience with multi-tenant AI applications.\n\n- Experience with recommendation or matching systems.\n\n- Experience working in a small team as the senior or sole AI engineer.\n\n- Experience with SOC 2 / ISO 27001-oriented AI security practices.\n\nSkills\nPython, Generative AI, FastAPI, RAG, PostgreSQL, AWS, Redis, Artificial Intelligence, LLM, VectorDB","description_format":"text","description_chars":3194,"description_truncated":false,"requirements":{"experience_years_min":4,"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":["Custom Software Development"],"lifecycle":[{"event":"open","at":"2026-09-29T12:05:09Z"}],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":1,"expected_fill_days":24,"reasons":["seen:1","velocity","win:early"],"computed_at":"2026-10-01T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/ajackus-senior-generative-ai-engineer","json_url":"https://alion.io/job/ajackus-senior-generative-ai-engineer.json","meta":{"generated_at":"2026-10-01T18:08:59Z","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":406,"day_limit":5000,"remaining_today":4594,"minute_limit":60,"resets_at":"2026-10-02T00:00:00Z"}}}