Senior AI Agent Engineer

About the Role

We are seeking an

engineer who doesn't just "talk" to LLMs but builds autonomous,

resilient systems. You will design multi-agent architecture that can reason,

use tools, and recover from failures independently.

Your primary goal

is to bridge the gap between "cool demos" and "production-grade

reliability." You will be responsible for deploying agents across various

business sectors (e.g., Finance, Operations, Customer Success), ensuring they are

not only intelligent but also safe, cost-effective, and predictable in a

production environment.

Key Responsibilities

• Agent Orchestration: Design and

implement stateful, multi-turn agent workflows using frameworks like LangGraph,

CrewAI, AutoGen, PydanticAI, Swarm, Haystack, or Bee Agent Framework.

• Proactive Reliability & Guardrails: Architect systems

that prevent production meltdowns. Implement circuit breakers,

"human-in-the-loop" triggers, and input/output guardrails to stop

infinite loops, prompt injections, and hallucinated tool calls before they

reach the end user.

• Multi-Sector Tooling: Build and maintain

high-precision API integrations (tools) that allow agents to interact with

diverse business systems (ERPs, CRMs, custom databases) deterministically.

• Observability & Tracing: Set up advanced

tracing (e.g., LangSmith, Langfuse, or Arize Phoenix) to debug complex

reasoning chains and monitor agent trajectories in real-time.

• Rigorous Evaluation (Evals): Develop automated

"Golden Datasets" and evaluation frameworks (using RAGas,

DeepEval, G-Eval, LangSmith Evaluators, or custom model-based grading) to

measure agent success rates and prevent regressions before every deployment.

• Cost & Latency Optimization: Manage the

"token budget" by implementing tiered model routing (e.g., using

Gemini 3 Flash for initial reasoning and Ultra for final verification) and

optimizing context window usage.

Requirements

Required Qualifications

• 3+ years of Software Engineering experience, with a background

in Python and FastAPI (or similar).

• 1+ year of experience specifically focused on

LLM-based Agents in a production environment.

• Deep Expertise in Agentic Patterns: Proven experience

implementing ReAct, Plan-and-Execute, or Multi-Agent Supervisor architectures.

• Production Infrastructure: Hands-on

experience with modern Vector Databases and Search Engines (e.g.,

Pinecone, Milvus, Weaviate, Qdrant, Chroma, or pgvector) and semantic caching

strategies.

• Robustness Mindset: A track record of

handling non-deterministic failures (e.g., implementing custom retry logic and

fallback strategies for failed tool calls).

Preferred Qualifications (The "Plus" Factors)

• Experience with Fine-tuning smaller models

(e.g., Llama 3) for specific tool-calling tasks to reduce latency.

• Knowledge of Data Privacy (handling PII in

agent prompts) and AI Security best practices.

• Prior experience building agents for specialized

sectors like Fintech or Supply Chain.