{"id":4443432,"url":"https://alion.io/job/enterprise-minds-ai-engineer-generative-ai","title":"AI Engineer - Generative AI","company":{"id":3800773,"name":"Enterprise Minds","domain":"eminds.ai","url":"https://alion.io/company/enterprise-minds","size_band":null,"is_staffing_agency":false,"employer_type":"services","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":["Bengaluru, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":5,"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":"Arize Phoenix","optional":false},{"name":"Asyncio","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"CI/CD","optional":false},{"name":"Docker","optional":false},{"name":"FastAPI","optional":false},{"name":"Flask","optional":false},{"name":"GCP","optional":false},{"name":"Gemini","optional":false},{"name":"Grafana","optional":false},{"name":"Hybrid Search","optional":false},{"name":"Kubernetes","optional":false},{"name":"LangChain","optional":false},{"name":"Langfuse","optional":false},{"name":"LangGraph","optional":false},{"name":"LangSmith","optional":false},{"name":"Llama","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"Milvus","optional":false},{"name":"Mistral","optional":false},{"name":"OpenAI","optional":false},{"name":"pgvector","optional":false},{"name":"Pinecone","optional":false},{"name":"Prometheus","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"Qdrant","optional":false},{"name":"RAG","optional":false},{"name":"Reranking","optional":false},{"name":"Rest API","optional":false},{"name":"Structured Outputs","optional":false},{"name":"Weaviate","optional":false},{"name":"Fine-tuning","optional":true},{"name":"LoRA","optional":true},{"name":"PEFT","optional":true},{"name":"PostgreSQL","optional":true},{"name":"QLoRA","optional":true},{"name":"Quantization","optional":true},{"name":"TensorRT","optional":true},{"name":"TensorRT-LLM","optional":true},{"name":"Triton","optional":true},{"name":"vLLM","optional":true}],"status":"live","first_seen_at":"2026-11-17T08:05:49Z","employer_posted_date":null,"last_verified_at":"2026-11-17T08:05:49Z","board_verified":false,"closed_at":null,"days_open":0,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":0},"description":"Job Description:\n\nAre you passionate about building intelligent AI applications and deploying them at scale in production? We are looking for a hands-on AI Engineer with practical experience in Generative AI, AI Agents, and production-grade AI solutions.\n\nIn this role, you will design, build, deploy, and monitor scalable LLM-powered applications and autonomous agent workflows.\n\nYou will bridge the gap between rapid AI prototyping and resilient cloud engineering - ensuring our AI systems are accurate, low-latency, cost-efficient, and reliable in live environments.\n\nRoles & Responsibilities:\n\n- Generative AI & RAG Development: Architect and implement end-to-end Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking strategies, embedding generation, hybrid search, and reranking.\n\n- Agentic AI Workflows: Design, orchestrate, and deploy multi-step, stateful AI agents and tool-using workflows utilizing frameworks such as LangChain and LangGraph.\n\n- Prompt Engineering & Model Optimization: Develop systematic prompt engineering, structured output generation, and evaluation frameworks to improve response accuracy, mitigate hallucinations, and optimize token usage and latency.\n\n- Production Deployment & API Integration: Package AI models and agent services into scalable, low-latency microservices and REST/streaming APIs using Python, Docker, and Kubernetes.\n\n- Cloud Infrastructure & MLOps: Build automated CI/CD pipelines, model versioning, and scalable cloud infrastructure across AWS, Azure, or GCP to support seamless production rollouts.\n\n- Observability, Monitoring & Guardrails: Implement production monitoring, distributed tracing, latency/cost tracking, and safety guardrails to detect drift, regressions, and edge-case failures in real time.\n\n- Cross-Functional Collaboration: Partner closely with product managers, backend engineers, and data teams to translate business requirements into measurable AI features.\n\nRequired Qualifications & Technical Skills:\n\n- Experience: 2+ years of hands-on experience building and deploying AI/ML or Generative AI applications into production environments.\n\n- Programming: Strong proficiency in Python, including asynchronous programming (asyncio), API frameworks (FastAPI/Flask), and clean software engineering practices.\n\n- GenAI & LLM Ecosystem: Practical experience working with foundational LLMs (OpenAI, Anthropic, Gemini, or open-source models like Llama/Mistral), Prompt Engineering, and RAG architectures (vector databases such as Pinecone, Weaviate, Qdrant, Milvus, or pgvector).\n\n- Agentic Frameworks: Hands-on experience building agentic workflows, tool-calling pipelines, and memory management using LangChain and LangGraph (or equivalent frameworks).\n\n- Cloud & Containerization: Solid working knowledge of cloud platforms (AWS, Azure, or GCP) and container orchestration using Docker and Kubernetes.\n\n- MLOps & Production Monitoring: Familiarity with MLOps workflows, automated LLM evaluation pipelines, and observability/tracing tools (e.g., LangSmith, Langfuse, Arize Phoenix, Prometheus, or Grafana).\n\nPreferred Qualifications:\n\n- Experience with LLM fine-tuning (LoRA/QLoRA), model quantization, and high-throughput inference engines (vLLM, TensorRT-LLM, or Triton).\n\n- Familiarity with AI security best practices, prompt-injection defense, and PII redaction guardrails.\n\n- Experience building streaming UIs or integrating AI backends with modern web applications.\n\nSkills\nArtificial Intelligence, Generative AI, LLM, Python, Agentic AI, LangChain, LangGraph, MLOps, FastAPI, RAG","description_format":"text","description_chars":3590,"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":["Artificial Intelligence","IT Consulting & Digital Transformation","Enterprise Apps Implementation Partners"],"lifecycle":[{"event":"open","at":"2026-11-17T08:34:15Z"}],"visa":[],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":30,"reasons":["seen:0","win:early"],"computed_at":"2026-11-17T10:21:12Z"},"pay":null,"html_url":"https://alion.io/job/enterprise-minds-ai-engineer-generative-ai","json_url":"https://alion.io/job/enterprise-minds-ai-engineer-generative-ai.json","meta":{"generated_at":"2026-11-17T10:21:12Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","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":18254,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-18T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.1,"usd":0.01,"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":3800773},"rest":"https://alion.io/mcp/rest/get_company?id=3800773"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fenterprise-minds-ai-engineer-generative-ai"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"free","price":{"credits":0,"usd":0},"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%2Fenterprise-minds-ai-engineer-generative-ai"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.1,"usd":0.01},"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%2Fenterprise-minds-ai-engineer-generative-ai"},{"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/enterprise-minds-ai-engineer-generative-ai\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fenterprise-minds-ai-engineer-generative-ai"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":4443432}},{"tool":"search_jobs","arguments":{"company":"eminds.ai","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":4443432},"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"}}