Lead Engineer (Langchain)

Epsilon ASI Corp.; Northern (KY); Hybrid; USD 120,000 - 180,000; Full time

Job summary

Epsilon ASI Corp. is seeking a mid-to-senior LangChain Engineer to join a remote AI engineering team building production-grade applications powered by large language models. You will design, develop, and optimize AI-powered workflows and agents, collaborating with engineers and stakeholders.

The ideal candidate has strong Python experience, hands-on LangChain or similar frameworks, and cloud deployment expertise. This role offers remote work with contract-to-hire potential.

Qualifications

• Proficiency in Python for AI applications.
• Hands-on experience with LangChain or similar LLM frameworks.
• Experience deploying AI applications in a major cloud environment (AWS).

Responsibilities

• Design and develop production-grade AI/LLM applications using LangChain and related frameworks.
• Build and integrate LLM-powered workflows, agents, and applications.
• Develop scalable backend services and APIs using Python.

Skills

Python

LangChain

LLM frameworks

AWS

APIs

Docker

Kubernetes

CI/CD

OpenAI/Anthropic etc.

Tools

Docker

Kubernetes

Job description

Help build the platforms that the world's best teams rely on.

Our work starts with the real artifacts of engineering: architecture notes, pull requests, runbooks, dashboards, incidents, and the constraints teams face every day. We make that context visible, then help turn it into systems that are clearer, stronger, and easier to operate.

We work from artifacts

Architecture notes, pull requests, runbooks, dashboards, incidents, and the actual constraints your team works inside.

We make context visible

The block gives the page more texture without making it feel like a stock-photo agency site.

Embark on a rewarding journey with us. Find opportunities to grow, learn and make a lasting impact.

Join a team that embraces forward-thinking ideas, fosters innovation, and cultivates an environment where your creativity can flourish.

People-First Mindset:

We think deeply about the real-world impact of every solution on teams, customers, and stakeholders.

Technical Integrity

Our work is grounded in best practices, thoughtful design, and sustainable engineering.

Long-Term Perspective

We’re invested in outcomes that endure, not quick fixes that falter.

A practical process for practical engineers.

The interview path should feel like the work: clear communication, systems thinking, technical judgment, and the ability to collaborate without ego.

01

A lightweight conversation about your background, what you want next, and the kinds of platform problems you like solving.

02

Walk through a real platform scenario and talk about tradeoffs, sequencing, observability, reliability, and team enablement.

03

Working session

Pair on a small practical exercise or artifact: architecture notes, implementation plan, review, or operational improvement.

04

Discuss role shape, expectations, compensation, client work, team norms, and how you do your best engineering work.

What working here should feel like

The benefits are designed around focus, trust, craft, and the reality that deep engineering work needs room.

Room for architecture, implementation, writing, review, and careful technical judgment.

A team that values context, humility, strong opinions, and better systems.

Work directly on the platform constraints that are slowing real engineering teams down.

Craft and learning

Kubernetes, cloud, modernization, AI workflows, and delivery systems in production contexts.

We care about secrets, access, change safety, auditability, and operational guardrails.

Modern tools

Use automation and AI carefully, with bounded context and human approval.

No mystery process, no puzzle interviews.

Open Positions

Be a part of a winning culture that fosters collaboration, creativity, and success in every career path

Location

United States

Employment Type

Full time

Location Type

Remote

Department

LangChain Engineer — Mid to Senior Level

Remote | Contract-to-Hire

About the Role

We are looking for a mid-to-senior level LangChain Engineer to join a growing AI engineering team building production-grade applications powered by large language models (LLMs).

In this role, you’ll work closely with engineers and technical stakeholders to design, develop, and optimize AI-powered applications and agentic workflows. The ideal candidate has strong Python experience, hands-on experience with LangChain or similar LLM frameworks, and experience deploying applications in a major cloud environment.

This is an excellent opportunity for an engineer who enjoys working at the intersection of software engineering, AI, and emerging LLM technologies and wants to have a meaningful impact on a growing team.

What You'll Do

Design and develop production-grade AI/LLM applications using LangChain and related frameworks

Build and integrate LLM-powered workflows, agents, and applications

Develop scalable backend services and APIs using Python

Integrate LLMs with external data sources, APIs, tools, and enterprise systems

Develop solutions involving prompt engineering, retrieval-augmented generation (RAG), tool calling, and AI agents

Deploy and maintain AI applications within a major cloud environment

Collaborate with engineers, product stakeholders, and clients to translate business requirements into technical solutions

Evaluate emerging AI/LLM technologies and identify opportunities to improve existing solutions

Write clean, maintainable, well-tested code suitable for production environments

Troubleshoot, optimize, and improve the performance, reliability, and scalability of AI applications

What We're Looking For

Mid-to-senior level software engineering experience

Strong proficiency in Python

Hands-on experience with LangChain or comparable LLM/AI application frameworks

Experience working with at least one major cloud platform:

AWS

Strong understanding of software engineering fundamentals, APIs, and application development

Experience building or integrating LLM-powered applications

Ability to work independently in a remote environment while collaborating effectively with a distributed team

Nice to Have

Experience with LangGraph

Experience building AI agents or agentic workflows

Experience with RAG, vector databases, embeddings, and semantic search

Familiarity with OpenAI, Anthropic, Gemini, or other foundation models

Experience with Docker and/or Kubernetes

Experience with CI/CD and production cloud deployments

Experience working in a consulting or client-facing environment

Education

A Bachelor's degree is not required if the candidate has strong relevant experience. Master's or PhD graduates with relevant hands-on experience in AI, machine learning, computer science, or a related field are encouraged to apply.

This role is not intended for candidates coming directly from an undergraduate program without professional or substantial project experience.

OpenTelemetry is best understood as a standard telemetry pipeline: APIs and SDKs create signals, context propagation links work across services, semantic conventions make data consistent, OTLP transports it, Collectors process it, and exporters deliver it to observability backends.

Coding-agent cost is not mainly the price of one clever prompt. It is the recurring cost of moving repository state, tool output, and loop history through paid models until useful work is accepted. Gateway observability makes that spend attributable and governable, while agent-loop discipline determines how much context gets sent.

Tool-using AI agents need more than prompt guidance. If an action can create a real side effect, enforcement should live in executable policy that can allow, deny, stop, or elevate before the tool call happens.

A practical way to distinguish DevOps, Platform Engineering, and SRE by responsibility instead of buzzword: collaboration, paved roads, and explicit reliability ownership.

Discover content that will transform your engineering organization.