Role Overview This is a deep-tech, hands-on AI engineering role focused on building production-grade AI systems, not demos. You will work on:

• RAG pipelines
• Multi-agent architectures
• LLM orchestration layers
• Real-time AI workflows

This role requires someone who has built and shipped AI systems at scale, understands latency, evaluation, and reliability trade-offs, and can turn LLM capabilities into real business outcomes.

What You’ll Build

AI Agents for Recruiting

1. Design and build multi-agent systems that automate sourcing, screening, follow-ups, and candidate evaluation.
2. Develop agent orchestration frameworks for complex, multi-step workflows.
3. Build systems that can reason, act, and iterate autonomously.

RAG & Knowledge Systems

1. Build and optimize RAG pipelines over structured + unstructured data (resumes, job descriptions, conversations).
2. Work with vector databases, embeddings, and retrieval strategies (HNSW, hybrid search, reranking).
3. Improve grounding, reduce hallucinations, and enhance response quality.

LLM Infrastructure & Performance

1. Optimize latency (TTFT), throughput, and cost for production systems.
2. Work on model optimization, quantization, caching, and batching strategies.
3. Build scalable inference systems using tools like vLLM, FastAPI, async pipelines.

Evaluation, Observability & Feedback Loops

1. Design evaluation frameworks for retrieval + generation quality.
2. Build feedback loops and telemetry pipelines to continuously improve model performance.
3. Track metrics like accuracy, latency, hallucination rate, and user outcomes.

Data & ML Pipelines

1. Build ETL and data pipelines for ingestion, processing, and feature generation.
2. Work with streaming systems (Kafka), batch systems, and real-time pipelines.
3. Enable continuous learning and improvement of AI systems.

Collaboration & Ownership

1. Work closely with backend engineers to integrate AI systems into product workflows.
2. Take ownership of systems from design → build → deploy → scale.
3. Contribute to hiring, architecture decisions, and engineering culture.

What We’re Looking For

• 3–7 years of experience in ML/AI engineering or applied AI roles.
• Strong hands-on experience with:
• LLMs (GPT, Llama, etc.)
• RAG architectures
• Embeddings & vector databases
• Experience building production-grade AI systems (not just prototypes).
• Strong programming skills in Python.
• Experience with FastAPI / Flask / async systems.
• Understanding of latency optimization, scaling, and cost trade-offs.
• Experience with data pipelines (PySpark, Airflow, etc.).
• Strong problem-solving and system design skills.