{"id":3008582,"url":"https://alion.io/job/cognium-ai-engineer-2","title":"AI Engineer","company":{"id":95983,"name":"Cognium","domain":"cognium.io","url":"https://alion.io/company/cognium","size_band":"11-50","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":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":["India"],"countries":["IN"],"hiring_countries":["IN"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":18500,"max_usd":39000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":8},"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":"Anthropic","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"CI/CD","optional":false},{"name":"Claude Code","optional":false},{"name":"Copilot","optional":false},{"name":"Cursor","optional":false},{"name":"Docker","optional":false},{"name":"FAISS","optional":false},{"name":"Fine-tuning","optional":false},{"name":"GCP","optional":false},{"name":"Hallucination","optional":false},{"name":"Kubernetes","optional":false},{"name":"LangChain","optional":false},{"name":"Llama","optional":false},{"name":"LlamaIndex","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"LoRA","optional":false},{"name":"Machine Learning","optional":false},{"name":"Mistral","optional":false},{"name":"OpenAI","optional":false},{"name":"pgvector","optional":false},{"name":"Pinecone","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"QLoRA","optional":false},{"name":"Quantization","optional":false},{"name":"Qwen","optional":false},{"name":"RAG","optional":false},{"name":"Ray Serve","optional":false},{"name":"TensorFlow","optional":false},{"name":"TGI","optional":false},{"name":"Triton","optional":false},{"name":"vLLM","optional":false},{"name":"Weaviate","optional":false},{"name":"Apache Kafka","optional":true},{"name":"AWQ","optional":true},{"name":"Computer Vision","optional":true},{"name":"Feature Store","optional":true},{"name":"GPTQ","optional":true},{"name":"Knowledge Distillation","optional":true},{"name":"Model Distillation","optional":true},{"name":"NLP","optional":true},{"name":"ONNX","optional":true},{"name":"PEFT","optional":true},{"name":"PostgreSQL","optional":true},{"name":"Ray","optional":true},{"name":"Recommender Systems","optional":true},{"name":"Spark","optional":true}],"status":"live","first_seen_at":"2026-10-21T14:35:30Z","employer_posted_date":null,"last_verified_at":"2026-10-21T14:35:30Z","board_verified":false,"closed_at":null,"days_open":0,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":0},"description":"We're looking for an AI Engineer who can move fluidly between research and production: someone who can prototype a new model or prompting approach quickly, then harden it into a reliable, observable, cost-efficient service that runs at scale. You'll work closely with product and full-stack engineering to turn ambiguous problems into shipped AI features.\n\nResponsibilities: \nDesign, build, and deploy machine learning and LLM-based systems, including retrieval-augmented generation (RAG) pipelines, fine-tuned models, and agentic workflows.\nOwn the full lifecycle of AI features: data collection and evaluation, model/prompt selection, experimentation, deployment, and monitoring in production.\nBuild and maintain data pipelines, embedding stores and vector databases that support search, retrieval, and personalization.\nEvaluate and integrate third-party model APIs (OpenAI, Anthropic, etc. ) alongside open-source and self-hosted models, balancing quality, latency, and cost.\nFine-tune, train, and deploy open-source models on our own infrastructure, including data prep, training/fine-tuning runs, quantization, and self-hosted inference serving at scale.\nEstablish evaluation frameworks and metrics to measure model quality, drift, hallucination rate, and business impact over time.\nCollaborate with full-stack engineers to expose AI capabilities through clean, well-documented APIs and SDKs.\nImplement guardrails, safety checks, and monitoring for AI systems running in production.\nStay current with the fast-moving AI/ML landscape and bring back practical recommendations on tools, models, and techniques.\nWrite clear technical documentation and communicate trade-offs to both technical and non-technical stakeholders.\n\nRequirements: \n4+ years of experience building and shipping machine learning or AI-powered systems in production.\nStrong Python skills, with hands-on experience using frameworks such as PyTorch, TensorFlow, or similar.\nPractical experience with large language model prompting, fine-tuning, RAG, or agent frameworks (e. g., LangChain, LlamaIndex, or custom implementations).\nHands-on experience training and fine-tuning open-source models (e. g., Llama, Mistral, Qwen) with full fine-tuning or parameter-efficient methods (LoRA/QLoRA) and deploying them on your own infrastructure rather than relying solely on hosted APIs.\nExperience standing up self-hosted inference serving on your own infra (e. g., vLLM, TGI, Triton, Ray Serve), including GPU provisioning, batching, and cost/latency optimization.\nSolid understanding of ML fundamentals: model evaluation, overfitting, data leakage, and experimentation methodology.\nExperience with vector databases and embedding-based retrieval (e. g., Pinecone, Weaviate, pgvector, FAISS).\nComfort working with cloud infrastructure (AWS, GCP, or Azure) and containerized deployments (Docker, Kubernetes), including GPU-backed compute.\nFamiliarity with MLOps practices, model versioning, CI/CD for ML, monitoring, and rollback strategies for both hosted and self-hosted models.\nStrong software engineering fundamentals: clean code, testing, code review, and API design.\nProficiency working with AI coding assistants (e. g., Claude Code, GitHub Copilot, Cursor) to accelerate development, while critically reviewing and validating AI-generated code.\nExcellent communication skills and comfort working in a remote, async-friendly environment.\n\nNice to Have: \nExperience with model quantization, distillation, or optimization techniques (e. g., GPTQ, AWQ, ONNX) for efficient self-hosted inference.\nBackground in NLP, computer vision, or recommendation systems.\nExperience with streaming data pipelines (Kafka, Spark) or feature stores.\nContributions to open-source ML/AI tooling.\nPrior experience in a startup or fast-growth environment.\nSkills\nAWS, Azure, Docker, GCP, Kubernetes, LangChain, LlamaIndex, PyTorch, Python, RAG, TensorFlow","description_format":"text","description_chars":3900,"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":["Machine Learning","Wealth Management & Financial Advisors"],"lifecycle":[{"event":"open","at":"2026-10-21T14:35:30Z"}],"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":7,"reasons":["seen:0","win:early"],"computed_at":"2026-10-22T06:10:10Z"},"pay":null,"html_url":"https://alion.io/job/cognium-ai-engineer-2","json_url":"https://alion.io/job/cognium-ai-engineer-2.json","meta":{"generated_at":"2026-10-22T06:52:34Z","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":2073,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-23T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"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":95983},"rest":"https://alion.io/mcp/rest/get_company?id=95983"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcognium-ai-engineer-2"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"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%2Fcognium-ai-engineer-2"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"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%2Fcognium-ai-engineer-2"},{"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/cognium-ai-engineer-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcognium-ai-engineer-2"}]}