Skills
RAG implementation
Custom chunking
Embeddings
Hybrid search
Re-ranking
Retrieval algorithms
Agentic programming
Agent state machines
Deterministic agent orchestration
Prompt engineering
Python
Async programming
Concurrency
Performance tuning
FastAPI
JSON Schema
Pydantic
HTTP clients
Unit testing
RAG regression testing
Prompt debugging
Observability
Tracing
Logging
Token and latency metrics
RAG
Hybrid Search
LLM APIs
Async Programming
Summary
A hands-on AI engineering role focused on building the mechanical core of RAG pipelines and agentic systems without relying heavily on abstraction layers. You will implement retrieval, embeddings, state machines, prompt construction, structured extraction, testing, and observability while optimizing systems for demanding enterprise workloads.
Highlights
Hands-on opportunity to build transparent, debuggable AI infrastructure from the ground up. The role offers deep ownership of RAG and agent systems, strong emphasis on performance, testing, observability, and enterprise-grade reliability.
Description
A hands-on builder who writes the native code powering RAG pipelines, agentic workflows, and context-engineering systems.
You will work close to the metal: no heavy frameworks, no magic abstractions: just transparent, debuggable AI infrastructure.
About the Role
You will implement the mechanical core of AI features: chunking logic, embedding flows, retrieval algorithms, agent state machines, and prompt-construction engines.
You will ensure every component is observable, testable, and optimized for enterprise workloads.
Skillset Requirements
· Native RAG Implementation: Custom chunking, embeddings, hybrid search, re-ranking, and retrieval logic.
· Agentic Programming: Building tool-use flows, working memory, state machines, and deterministic agent orchestration.
· Prompt Engineering: Crafting structured prompts, multi-shot reasoning scaffolds, and domain-specific context packing.
· Python Engineering: Strong fundamentals, async programming, concurrency, and performance tuning.
· FastAPI: Building transparent, debuggable AI microservices.
· Structured Extraction: JSON schema design, Pydantic models, and deterministic extraction patterns.
· LLM Tooling: Experience with HTTP clients, raw API calls, and minimal-framework AI development.
· Testing & Debugging: Unit tests for agents, RAG regression tests, and prompt-level debugging
· Observability: Instrumenting tracing, logging, and token/latency metrics for agents and RAG components.
Regards
Mohd Faisal
908-279-1281
faisal@clifyx.com
