{"id":1571629,"url":"https://alion.io/job/vy-systems-generative-ai-engineer","title":"Generative AI Engineer","company":{"id":3801566,"name":"Vy Systems","domain":"vysystems.jobs","url":"https://alion.io/company/vy-systems","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":"middle","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"explicit","locations":["Bengaluru, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":21000,"max_usd":53000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":22},"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"Chroma","optional":false},{"name":"CI/CD","optional":false},{"name":"Claude","optional":false},{"name":"Django","optional":false},{"name":"Docker","optional":false},{"name":"Embeddings","optional":false},{"name":"FAISS","optional":false},{"name":"FastAPI","optional":false},{"name":"Flask","optional":false},{"name":"Function Calling","optional":false},{"name":"GCP","optional":false},{"name":"Gemini","optional":false},{"name":"Git","optional":false},{"name":"LangChain","optional":false},{"name":"LangGraph","optional":false},{"name":"LlamaIndex","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"OpenAI","optional":false},{"name":"Pinecone","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Rest API","optional":false},{"name":"Semantic Search","optional":false},{"name":"Semantic Search","optional":false},{"name":"SQL","optional":false},{"name":"Structured Outputs","optional":false},{"name":"Tool Use","optional":false},{"name":"Weaviate","optional":false},{"name":"Hugging Face","optional":true},{"name":"Kubernetes","optional":true},{"name":"Llama","optional":true},{"name":"Mistral","optional":true},{"name":"Multi-Agent Systems","optional":true},{"name":"NLP","optional":true},{"name":"PyTorch","optional":true},{"name":"Qwen","optional":true}],"status":"live","first_seen_at":"2026-10-01T06:52:37Z","employer_posted_date":null,"last_verified_at":"2026-10-01T06:52:37Z","board_verified":false,"closed_at":null,"days_open":1,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":1},"description":"Role : Python + Generative AI Engineer\n\nLocation : Bangalore, India\n\nExperience : 4+ Years\n\nEmployment Type : Full-time\n\nJob Summary : \n\nWe are looking for an experienced Python + Generative AI Engineer with 4+ years of software development experience and strong hands-on expertise in Generative AI, LLMs, and AI application development. The ideal candidate will design and build scalable AI-powered solutions using Python, LLMs, RAG architectures, vector databases, and modern AI frameworks.\n\nKey Responsibilities : \n\n- Design, develop, and deploy AI/GenAI applications using Python.\n\n- Build LLM-powered applications using models such as OpenAI GPT, Azure OpenAI, Claude, Gemini, or open-source LLMs.\n\n- Develop Retrieval-Augmented Generation (RAG) pipelines for enterprise use cases.\n\n- Work with vector databases such as FAISS, Pinecone, Chroma, Weaviate, or equivalent technologies.\n\n- Develop AI agents, tool-calling workflows, and multi-step LLM applications.\n\n- Use frameworks such as LangChain, LangGraph, LlamaIndex, or similar frameworks.\n\n- Develop REST APIs and backend services using FastAPI, Flask, or Django.\n\n- Implement prompt engineering, prompt optimization, structured outputs, and LLM evaluation techniques.\n\n- Work with document processing, embeddings, chunking, metadata extraction, and semantic search.\n\n- Integrate GenAI solutions with enterprise applications, databases, and third-party APIs.\n\n- Implement monitoring, logging, security, guardrails, and responsible AI practices.\n\n- Optimize applications for latency, scalability, reliability, and cost.\n\n- Collaborate with data scientists, ML engineers, product teams, and software engineers.\n\n- Participate in code reviews, technical design discussions, testing, and production deployment.\n\nRequired Skills : \n\n- 4+ years of professional software development experience\n\n- Strong proficiency in Python\n\n- Hands-on experience with Generative AI / LLM applications\n\n- Experience with RAG architecture\n\n- Strong understanding of : \n\n1. Prompt engineering\n\n2. Embeddings\n\n3. Vector search\n\n4. Semantic search\n\n5. Context windows\n\n6. LLM inference\n\n7. Function/tool calling\n\n8. AI agents\n\n- Experience with LangChain / LangGraph / LlamaIndex\n\n- Experience with at least one vector database such as FAISS, Pinecone, Chroma, or Weaviate\n\n- Experience building APIs using FastAPI / Flask / Django\n\n- Good understanding of REST APIs, JSON, Git, and software development practices\n\n- Experience with SQL and/or NoSQL databases\n\n- Familiarity with cloud platforms such as AWS, Azure, or GCP\n\n- Understanding of Docker and CI/CD practices\n\nGood to Have : \n\n- Experience with Azure OpenAI\n\n- Experience with open-source models such as Llama, Mistral, or Qwen\n\n- Experience with agentic AI and multi-agent systems\n\n- Knowledge of ML/NLP fundamentals\n\n- Experience with LLM evaluation and observability tools\n\n- Knowledge of Kubernetes\n\n- Experience deploying AI applications in production\n\n- Familiarity with PyTorch or Hugging Face Transformers\n\nEducation : \n\n- Bachelor's or Master's degree in Computer Science, Engineering, AI/ML, or a related field is preferred.\nSkills\nPython, Generative AI, LangChain, RAG, FastAPI, LLM, Flask, Django, Artificial Intelligence","description_format":"text","description_chars":3229,"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":[{"name":"India","iso":"IN","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-10-01T08:00:00Z"}],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":0,"expected_fill_days":19,"reasons":["seen:0","velocity","win:early"],"computed_at":"2026-10-02T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/vy-systems-generative-ai-engineer","json_url":"https://alion.io/job/vy-systems-generative-ai-engineer.json","meta":{"generated_at":"2026-10-03T04:15:57Z","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":4405,"day_limit":5000,"remaining_today":595,"minute_limit":60,"resets_at":"2026-10-04T00:00:00Z"}}}