{"id":1234946,"url":"https://alion.io/job/unicoconnect-ai-engineer","title":"AI Engineer","company":{"id":2044637,"name":"Unico Connect","domain":"unicoconnect.com","url":"https://alion.io/company/unicoconnect","size_band":"51-200","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":"junior","employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"inferred_city","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":["Mumbai, India"],"countries":["IN"],"hiring_countries":["IN"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":11500,"max_usd":31000,"period":"year","method":"role_seniority_country_cell","sample_n":14},"experience_years_min":2,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Agentic Workflows","optional":false},{"name":"AI Agents","optional":false},{"name":"Amazon EC2","optional":false},{"name":"Amazon S3","optional":false},{"name":"Amazon SageMaker","optional":false},{"name":"Anthropic","optional":false},{"name":"AutoGen","optional":false},{"name":"AWS","optional":false},{"name":"AWS Bedrock","optional":false},{"name":"Chroma","optional":false},{"name":"Claude","optional":false},{"name":"CrewAI","optional":false},{"name":"Embeddings","optional":false},{"name":"FastAPI","optional":false},{"name":"Function Calling","optional":false},{"name":"Gemini","optional":false},{"name":"Hallucination","optional":false},{"name":"Hybrid Search","optional":false},{"name":"IAM","optional":false},{"name":"Langfuse","optional":false},{"name":"LangGraph","optional":false},{"name":"LangSmith","optional":false},{"name":"Llama","optional":false},{"name":"LlamaIndex","optional":false},{"name":"LLM","optional":false},{"name":"LLM Evaluation","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"Mistral","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Ollama","optional":false},{"name":"OpenAI","optional":false},{"name":"OpenTelemetry","optional":false},{"name":"pgvector","optional":false},{"name":"Pinecone","optional":false},{"name":"Prompt Caching","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"Qdrant","optional":false},{"name":"Qwen","optional":false},{"name":"RAG","optional":false},{"name":"Reranking","optional":false},{"name":"Structured Outputs","optional":false},{"name":"Tool Use","optional":false},{"name":"vLLM","optional":false},{"name":"Weaviate","optional":false},{"name":"DeepEval","optional":true},{"name":"LangChain","optional":true},{"name":"LoRA","optional":true},{"name":"PEFT","optional":true},{"name":"PostgreSQL","optional":true},{"name":"Promptfoo","optional":true},{"name":"QLoRA","optional":true},{"name":"Ragas","optional":true},{"name":"Transformers","optional":true}],"status":"live","first_seen_at":"2026-09-15T08:29:44Z","employer_posted_date":null,"last_verified_at":"2026-09-15T08:29:44Z","board_verified":false,"closed_at":null,"days_open":18,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":18},"description":"AI Engineer\nLLMs, Agents & AI Services\n📍 Mumbai (On-site) | Full-time | 2-4 years\n\nAbout the Role:\nUnico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies.\nAI is core to how we design, deliver, and scale software for our customers.\nWe are hiring an AI Engineer for a dedicated client engagement building a complex production AI platform, working on the AI capabilities and agentic features at the core of the product.\nThe mandatory requirement for this role is at least one AI feature personally shipped to production for real users, with operational ownership.\nThe role suits someone who thinks quickly on solutioning, can take an ambiguous problem to a working prototype in days, and has the discipline to carry it through to production with predictable economics.\nYou will work alongside the Senior AI Engineer and the wider pod, with ownership of parts of the AI surface area of the product.\n\nResponsibilities:\nSolutioning and POCs\nTranslate ambiguous customer problems into working POCs at speed.\nPick the right model, framework, and architecture, and demonstrate value early before scaling investment.\n\nLLM Application Development\nBuild AI features and services using LLM APIs from OpenAI, Anthropic, Google, and self-hosted open-weight models (Llama, Qwen, Mistral).\nChoose the right model per use case based on cost, latency, capability, and context-window trade-offs.\n\nAgentic System Design\nDesign and implement agentic workflows using LangGraph, CrewAI, AutoGen, LlamaIndex Agents, or custom orchestration.\nCover tool use, planning, memory, and multi-step reasoning appropriate to the problem.\n\nAPI and Service Development\nBuild production AI services and APIs using Python and FastAPI.\nHandle streaming responses, async processing, structured outputs, retries, and graceful degradation when models or tools fail.\n\nRetrieval and Tool Integration\nImplement RAG pipelines with vector databases (Pinecone, Weaviate, Qdrant, pgvector, Chroma), embeddings, chunking strategies, hybrid search, and reranking.\nIntegrate external tools, internal APIs, and document sources through tool-calling and MCP-style patterns.\n\nCost Analysis and Unit Economics\nModel the per-request and per-user cost of every AI feature before it ships.\nTrack token usage, prompt caching, batching, and model-routing strategies.\nDrive measurable improvements in unit economics.\n\nProduction Hardening\nAdd observability and tracing (LangSmith, Langfuse, OpenTelemetry), guardrails, content safety checks, prompt injection defences, and fallback behaviour.\n\nPrompt Engineering and Evaluation\nDesign, test, and iterate prompts with measured outcomes.\nBuild evaluation harnesses for accuracy, hallucination, latency, and cost.\nRun benchmarks across models and prompt variants before locking in a design.\n\nRequirements:\nAI Feature Shipped to Production (Mandatory)\nMust have personally built and shipped at least one AI feature that runs in production for real users, with operational ownership.\nPOCs, internal demos, and one-off scripts do not qualify.\n\n2 to 4 Years of Professional Software or AI Engineering Experience\nWith at least one production AI feature owned end to end.\n\nStrong Python Proficiency and API Development with FastAPI\nComfort with type hints, async, packaging, testing, streaming responses, and authentication.\nProduction-grade Python, not notebook-only code.\n\nHands-on Depth Across the LLM and Agent Stack\nWorking experience with at least two of OpenAI, Anthropic Claude, Google Gemini, or self-hosted open-weight models (vLLM, Ollama, Together, Replicate).\nWorking familiarity with at least one agent framework (LangGraph, CrewAI, AutoGen, LlamaIndex Agents) or hand-rolled equivalent.\nWorking knowledge of RAG, embeddings, and vector databases (Pinecone, Weaviate, Qdrant, pgvector, Chroma).\n\nSolutioning Speed and POC Velocity\nDemonstrated ability to move from a fuzzy problem to a working prototype in days.\nStrong instinct for what to build first, what to defer, and what to throw away.\n\nCost Discipline for Production AI\nAbility to calculate, monitor, and optimise the cost of LLM APIs, tokens, embeddings, vector store usage, and infrastructure.\nTreats unit economics as a first-class concern.\n\nAWS Familiarity\nWorking knowledge of EC2, S3, IAM, and at least one of Bedrock, SageMaker, or equivalent.\n\nComfortable in a Fast-Moving Environment\nSelf-directed, comfortable with ambiguity, takes ownership without being asked, and ships under shifting priorities.\n\nStrong Written and Spoken English Communication\nAble to explain trade-offs to non-AI engineers, designers, product managers, and clients in plain language.\n\nNice to Have\nfine-tuning or LoRA, QLoRA, PEFT exposure\nMCP server authoring\neval framework experience (LangSmith, Promptfoo, Ragas, DeepEval)\nopen-source AI contributions\nmulti-modal models (vision, audio)\nSkills\nPython, Large Language Models (LLM), Generative AI, LangGraph, FastAPI, Retrieval Augmented Generation (RAG), AI Agents, OpenAI, Anthropic Claude, Google Gemini, Vector database, Prompt engineering","description_format":"text","description_chars":5109,"description_truncated":false,"requirements":{"experience_years_min":2,"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":["Mobile App Development Services","Custom Software Development","AI Consulting & Integration"],"lifecycle":[{"event":"open","at":"2026-09-25T16:00:00Z"}],"visa":[],"liveness":{"score":62,"band":"ok","label":"Likely open","p_open":0.85,"p_active":0.815,"p_room":0.9,"age_days":17,"expected_fill_days":31,"reasons":["seen:17","velocity","win:mid","comp:junior"],"computed_at":"2026-10-03T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/unicoconnect-ai-engineer","json_url":"https://alion.io/job/unicoconnect-ai-engineer.json","meta":{"generated_at":"2026-10-04T03:02:04Z","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":4596,"day_limit":5000,"remaining_today":404,"minute_limit":60,"resets_at":"2026-10-05T00:00:00Z"}}}