{"id":1227074,"url":"https://alion.io/job/qentelli-lead-ai-engineer","title":"Lead AI Engineer","company":{"id":1798376,"name":"Qentelli","domain":"qentelli.com","url":"https://alion.io/company/qentelli","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":"lead","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Hyderabad, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":22000,"max_usd":48000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":28},"experience_years_min":6,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"A/B Testing","optional":false},{"name":"Agentic Workflows","optional":false},{"name":"AI Agents","optional":false},{"name":"Amazon SageMaker","optional":false},{"name":"Anthropic","optional":false},{"name":"AWS","optional":false},{"name":"AWS Bedrock","optional":false},{"name":"Azure","optional":false},{"name":"CI/CD","optional":false},{"name":"Claude","optional":false},{"name":"Embeddings","optional":false},{"name":"FAISS","optional":false},{"name":"Falcon","optional":false},{"name":"Fine-tuning","optional":false},{"name":"GCP","optional":false},{"name":"Gemini","optional":false},{"name":"Hallucination","optional":false},{"name":"LangChain","optional":false},{"name":"Llama","optional":false},{"name":"LlamaIndex","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"LLMOps","optional":false},{"name":"LoRA","optional":false},{"name":"Machine Learning","optional":false},{"name":"Milvus","optional":false},{"name":"Mistral","optional":false},{"name":"OpenAI","optional":false},{"name":"PEFT","optional":false},{"name":"pgvector","optional":false},{"name":"Pinecone","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"QLoRA","optional":false},{"name":"RAG","optional":false},{"name":"RLHF","optional":false},{"name":"Semantic Kernel","optional":false},{"name":"Semantic Search","optional":false},{"name":"Semantic Search","optional":false},{"name":"Vertex AI","optional":false},{"name":"Weaviate","optional":false},{"name":"PostgreSQL","optional":true},{"name":"Transformers","optional":true}],"status":"live","first_seen_at":"2026-09-25T12:01:08Z","employer_posted_date":null,"last_verified_at":"2026-09-25T12:01:08Z","board_verified":false,"closed_at":null,"days_open":8,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":8},"description":"Job Summary:\n\nWe are seeking a Lead AI Engineer to drive the design, development, and deployment of our conversational AI and generative AI systems, including LLM-powered chatbots, Retrieval-Augmented Generation (RAG) pipelines, and agentic AI applications. This is a hands-on technical leadership role - you'll architect production-grade AI systems, guide a team of AI/ML engineers, and work closely with Product and Data Engineering to deliver reliable, scalable, and safe AI experiences.\n\nKey Responsibilities:\n\n- Architect and lead development of LLM-based applications, including chatbots, virtual assistants, and copilots.\n\n- Design and implement RAG pipelines - including chunking strategies, embedding generation, vector search, re-ranking, and prompt construction.\n\n- Build and maintain agentic workflows using frameworks such as LangChain, LlamaIndex, or custom orchestration layers.\n\n- Design prompt engineering and prompt management systems, including versioning and A/B testing of prompts.\n\n- Implement evaluation frameworks for LLM output quality - hallucination detection, relevance scoring, latency, and safety benchmarks.\n\n- Build robust MLOps/LLMOps pipelines for model deployment, monitoring, versioning, and rollback (CI/CD for AI systems).\n\n- Ensure systems are designed for low latency, scalability, and cost-efficiency in production environments.\n\n- Collaborate with Data Engineering to ensure clean, structured data feeds into embeddings and knowledge bases.\n\n- Implement guardrails, content moderation, and safety mechanisms to mitigate prompt injection, data leakage, and harmful outputs.\n\n- Mentor and provide technical leadership to a team of AI/ML engineers; conduct design and code reviews.\n\n- Stay current with the fast-evolving GenAI/LLM landscape and evaluate new tools, models, and techniques for adoption.\n\nRequired Skills & Qualifications:\n\n- 6+ years of experience in AI/ML engineering, with 2+ years in a lead or senior technical capacity.\n\n- Strong programming skills in Python, with production experience in ML/AI systems.\n\n- Hands-on experience building LLM applications: chatbots, RAG systems, or generative AI products in production.\n\n- Practical experience with RAG components: chunking strategies, embedding models, vector databases, retrieval and re-ranking.\n\n- Experience with LLM orchestration frameworks: LangChain, LlamaIndex, Semantic Kernel, or similar.\n\n- Experience working with LLM APIs and platforms (OpenAI, Anthropic Claude, Google Gemini) and/or hosting open-source LLMs (Llama, Mistral, Falcon).\n\n- Familiarity with fine-tuning techniques (LoRA, QLoRA, PEFT, RLHF) and when to apply them vs. prompting/RAG.\n\n- Experience with vector databases and semantic search (Pinecone, Weaviate, Milvus, FAISS, pgvector).\n\n- Solid understanding of MLOps/LLMOps practices: model versioning, monitoring, A/B testing, CI/CD for ML.\n\n- Experience with cloud AI platforms (AWS Bedrock/SageMaker, GCP Vertex AI, Azure OpenAI).\n\n- Strong grasp of evaluation methodologies for generative AI (hallucination rate, groundedness, relevance, latency/cost trade-offs).\n\n- Understanding of AI safety and responsible AI practices - guardrails, bias mitigation, prompt injection defense.\n\n- Experience mentoring engineers, driving architecture decisions, and leading technical roadmaps.\nSkills\nPython, Generative AI, LangChain, Machine Learning, Vertex AI, Conversational AI, Artificial Intelligence, Chatbot, RAG","description_format":"text","description_chars":3444,"description_truncated":false,"requirements":{"experience_years_min":6,"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":"2026-09-25T13:06:44Z"}],"visa":[],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":7,"expected_fill_days":24,"reasons":["seen:7","velocity","win:early"],"computed_at":"2026-10-03T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/qentelli-lead-ai-engineer","json_url":"https://alion.io/job/qentelli-lead-ai-engineer.json","meta":{"generated_at":"2026-10-04T02:24:05Z","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":3410,"day_limit":5000,"remaining_today":1590,"minute_limit":60,"resets_at":"2026-10-05T00:00:00Z"}}}