AI Engineer

CyberCoders; Sacramento (CA); On-site; USD 150,000 - 190,000; Full time

Benefits offered by this job

Medical

Dental

Vision

401k w 4% match

PTO

Hybrid flex

Job summary

CyberCoders in California seeks an experienced AI Engineer to design, build, and deploy production-grade AI systems leveraging LLMs, RAG, and vector databases. You will work with LangChain and Microsoft Agent integrations to enable multi-turn, context-aware interactions.

Join a healthcare technology company focused on improving lives, collaborating with product, data science, and software engineering to translate business requirements into scalable services.

Qualifications

• 3+ years of professional software engineering experience.
• 2+ years focused on machine learning or AI systems.
• Proven expertise in Python and production software development practices.
• Hands‑on experience with LLMs and building applications around them.
• Experience with LangChain and building composable LLM pipelines and agents.
• Experience implementing RAG systems and connecting LLMs to external knowledge via retrieval.
• Knowledge of API design, microservices, containerization (Docker), and orchestration (Kubernetes).
• Nice to have: MS/PhD or open-source contributions.

Responsibilities

• Design, implement, and maintain end‑to‑end AI solutions using LLMs, RAG, and conversational agents.
• Develop LangChain pipelines and Microsoft Agent integrations for multi‑turn interactions.
• Integrate vector databases (ChromaDB, Pinecone) and Azure AI Search for efficient retrieval.
• Build robust prompt engineering, context management, and grounding strategies.
• Monitor performance, latency, hallucination rates, and user feedback in production.
• Collaborate with product, data science, and software engineering to translate requirements into scalable designs.
• Write clean Python code, APIs, and microservices; participate in CI/CD pipelines.
• Optimize inference cost and latency through model selection and infrastructure tuning.

Skills

Python programming

LLMs / AI systems

LangChain

API design

CI/CD practices

Azure familiarity

Education

Bachelors or Masters in CS or Engineering

Tools

Docker

Kubernetes

PyTorch

TensorFlow

ChromaDB

Pinecone

Azure AI Search

Job description

AI Engineer

Company Overview

We are a healthcare technology company located in the Davis, CA area. We have proudly been in business for over 25 years and have built some of the most innovative technology in the healthcare industry. We are very passionate about improving healthcare and saving lives across the country!

Position Overview

We are seeking an experienced AI Engineer to design, build, and deploy production-grade AI systems that leverage large language models, retrieval-augmented generation (RAG), and modern vector databases. The ideal candidate will combine strong software engineering discipline with hands‑on experience in LLMs, LangChain, Microsoft Agent frameworks, and scalable search and vector storage solutions such as ChromaDB and Pinecone. You will work cross‑functionally to turn research and prototypes into reliable, maintainable services that deliver measurable business value.

Key Responsibilities

• Design, implement, and maintain end‑to‑end AI solutions that incorporate LLMs, RAG architectures, and conversational agents.
• Develop and extend LangChain‑based pipelines and Microsoft Agent integrations to enable multi‑turn, context‑aware interactions.
• Integrate and manage vector databases (ChromaDB, Pinecone) and Azure AI Search to support efficient retrieval and similarity search workflows.
• Build robust prompt engineering, context management, and grounding strategies to improve accuracy and reliability of generated outputs.
• Implement model evaluation, monitoring, and logging to track performance, latency, hallucination rates, and user feedback in production.
• Collaborate with product managers, data scientists, and software engineers to translate business requirements into scalable technical designs.
• Write clean, well‑tested Python code, APIs, and microservices; participate in code reviews and maintain CI/CD pipelines.
• Optimize inference cost and latency through model selection, caching, batching, and infrastructure tuning (including Azure deployments).
• Research and prototype new models, tools, and techniques to continuously improve system capabilities and user experience.
• Document system design, runbooks, and operation procedures; provide support during incidents and production rollouts.

Qualifications

• Bachelors or Masters degree in Computer Science, Engineering, or a related field (or equivalent experience).
• 3+ years of professional software engineering experience, with a minimum of 2 years focused on machine learning or AI systems.
• Proven expertise in Python and production software development best practices (testing, CI/CD, version control).
• Hands‑on experience with LLMs and building applications around them (prompting, fine‑tuning, instruction tuning, or adapters).
• Practical experience with LangChain and building composable LLM pipelines and agents.
• Experience implementing RAG systems and connecting LLMs to external knowledge via retrieval.
• Familiarity with Microsoft Agent frameworks and integrating conversational agents into products.
• Hands‑on experience with vector databases or stores such as ChromaDB and Pinecone.
• Experience integrating and tuning Azure AI Search or equivalent cloud search services; comfort working in Azure.
• Knowledge of ML/DL frameworks such as PyTorch or TensorFlow, and model deployment tools.
• Strong understanding of API design, microservices, containerization (Docker), and orchestration (Kubernetes preferred).
• Excellent problem‑solving skills, attention to detail, and ability to communicate technical concepts clearly to cross‑functional teams.
• Nice to have: contributions to open‑source projects, prior experience in productionizing LLMs at scale, or advanced degree (MS/PhD).

Benefits

• Medical
• Dental
• Vision
• 401k w 4% match
• PTO
• Hybrid flex