Website:
finarb.ai
Job details:
AI EngineerLLM Applications & Agentic Systems · Full-time · Mid-level (2–4 years) · Remote (India) or on-site
Large language models are moving from demos to dependable products, and we’re building the systems that make that happen. We’re looking for an AI Engineer to design, build, and ship production-grade agentic applications — the kind that reason over real financial and business data, chain skills and tools reliably, and hold up under real-world load.
About UsFinArb is a data-driven analytics firm that began by solving complex business problems through large-scale data engineering, analysis, and predictive modeling, and now focuses on building automated, scalable solutions for clients. The team consists of dedicated analytics professionals with around two decades of combined experience in machine learning, artificial intelligence, and deep learning across multiple industry verticals — especially banking, trading, risk, and finance. FinArb has strong expertise in data ETL, algorithm development, and dashboard/visualization creation in areas such as marketing analytics, customer analytics, NLP/text modeling, image processing, financial analytics, equity valuation, trading algorithms, and credit risk analytics.
About the RoleTwelve months in, you will have shipped agentic features that users rely on every day: multi-step LLM workflows built on LangChain and LangGraph, retrieval pipelines grounded in clean, well-understood data, and an evaluation harness that tells us — with numbers, not vibes — whether each release got better. You’ll work closely with product and data teams, own your systems end to end, and raise the bar for how we build with LLMs.
What You’ll Do• Design and ship agentic applications end to end — planning, tool use, skill chaining, and multi-agent workflows — using LangChain, LangGraph, and related orchestration frameworks.
• Build and chain agent skills — develop reusable skills (tools, functions, and capabilities) and compose them into multi-step skill chains that solve complex analytical workflows reliably.
• Build LLM orchestration pipelines that integrate models with APIs, databases, and internal services, with sensible state management, retries, and fallbacks.
• Own the data behind the AI — source, clean, structure, and chunk data for retrieval-augmented generation (RAG); choose and tune embeddings and vector stores.
• Measure what you ship — design evals and test sets, track quality metrics, and apply basic statistics to separate real improvements from noise.
• Harden systems for production — observability, tracing, guardrails, latency and cost optimization (model routing, caching, prompt design).
• Collaborate and communicate — work with product, data, and engineering peers to turn ambiguous problems into shippable AI features.
What We’re Looking ForRequired
• 2–4 years of software or ML engineering experience, including hands-on experience building LLM-powered applications.
• Strong Python and experience with LLM orchestration frameworks — LangChain and LangGraph specifically, or deep experience with comparable tools (LlamaIndex, Semantic Kernel, CrewAI, AutoGen).
• Experience building agentic systems: designing agent skills, skill chaining, tool/function calling, state and memory management, and multi-step reasoning workflows.
• Strong data understanding — comfortable with SQL, data pipelines, data quality, embeddings, and preparing messy real-world data for retrieval and model consumption.
• Working understanding of machine learning fundamentals: how models are trained and evaluated, common failure modes, and when to use (and not use) an LLM.
• Basic statistics: distributions, sampling, significance testing, and enough rigor to design and interpret A/B tests and offline evals.
Nice to Have
• Production RAG experience with vector databases (pgvector, Pinecone, Qdrant, Weaviate) and hybrid search.
• Familiarity with LLM observability and eval tooling (LangSmith, Braintrust, Helicone) and prompt-caching mechanics.
• Experience with Model Context Protocol (MCP), guardrails/safety patterns (e.g. OWASP LLM Top 10), or fine-tuning.
• Cloud deployment experience (AWS/GCP/Azure), containerization, and CI/CD for ML systems.
Click on Apply to know more.