Forward Deployed Engineer

Elios AI; Boston (MA); On-site; USD 140,000 - 200,000; Full time

Job summary

Elios AI seeks Forward Deployed Engineers to design and deploy AI systems in real-world environments, embedding client solutions that integrate LLMs, data infrastructure, and operational workflows.

In this role you will craft production-grade systems rather than demos, owning end-to-end delivery and iterating on live feedback with real users and stakeholders across projects with diverse data sources.

Qualifications

• 3–8+ years of software engineering experience in production systems.
• Strong proficiency in Python and/or TypeScript.
• Experience designing distributed, data-intensive applications.
• Experience building APIs and data pipelines.
• Familiarity with cloud infrastructure and containerized deployments.
• Ability to communicate complex system design to non-technical stakeholders.

Responsibilities

• Design and deploy LLM-powered applications using APIs (OpenAI, Anthropic, open-source models).
• Build agent-based systems with orchestration frameworks (LangChain, LangGraph, custom agents).
• Develop evaluation pipelines for non-deterministic outputs (prompt testing, scoring, guardrails).
• Build and optimize data pipelines (batch + streaming) using Airflow, Kafka, or similar.
• Design data models and integrate structured/unstructured data sources (APIs, warehouses, document stores).
• Work with data platforms such as Snowflake, Databricks, BigQuery, or Postgres.
• Implement caching, indexing, and retrieval strategies for performance and cost optimization.
• Build scalable backend services and APIs (Python, FastAPI, Node.js, TypeScript).
• Deploy services using Docker, Kubernetes, and cloud platforms (AWS, GCP, Azure).
• Implement CI/CD pipelines and versioning for models, prompts, and workflows.
• Manage secrets, auth, and secure system integrations in production environments.
• Design multi-step agent workflows with tool use, memory, and state management.
• Implement function calling, tool routing, and structured output handling.
• Build systems that combine LLM reasoning with deterministic business logic.
• Work directly with stakeholders to translate business problems into technical systems.
• Iterate rapidly in live environments with real users and feedback loops.

Skills

Python

TypeScript

Distributed systems

APIs

Data pipelines

Cloud infrastructure

Docker

Kubernetes

Tools

Airflow

Kafka

Snowflake

Databricks

BigQuery

Postgres

LangChain

LangGraph

Job description

Overview

We’re hiring Forward Deployed Engineers to build and deploy AI systems in real-world environments.

This is a client-embedded engineering role. You will take ambiguous problems, design technical solutions, and ship production systems that integrate LLMs, data infrastructure, and operational workflows. You are not building demos—you are building systems that are used, measured, and iterated on.

What You’ll Do

Build Production AI Systems

• Design and deploy LLM-powered applications using APIs (OpenAI, Anthropic, open-source models)
• Build agent-based systems using orchestration frameworks (LangChain, LangGraph, custom agents)
• Develop evaluation pipelines for non-deterministic outputs (prompt testing, scoring, guardrails)
• Build and optimize data pipelines (batch + streaming) using tools like Airflow, Kafka, or similar
• Design data models and integrate structured/unstructured data sources (APIs, warehouses, document stores)
• Work with data platforms such as Snowflake, Databricks, BigQuery, or Postgres
• Implement caching, indexing, and retrieval strategies for performance and cost optimization
• Build scalable backend services and APIs (Python, FastAPI, Node.js, TypeScript)
• Deploy services using Docker, Kubernetes, and cloud platforms (AWS, GCP, Azure)
• Implement CI/CD pipelines and versioning for models, prompts, and workflows
• Manage secrets, auth, and secure system integrations in production environments

Agentic Workflows & Automation

• Design multi-step agent workflows with tool use, memory, and state management
• Implement function calling, tool routing, and structured output handling
• Build systems that combine LLM reasoning with deterministic business logic

Client-Embedded Execution

• Work directly with stakeholders to translate business problems into technical systems
• Iterate rapidly in live environments with real users and feedback loops

What You Bring

• 3–8+ years of software engineering experience
• Strong proficiency in Python and/or TypeScript
• Experience building distributed systems, APIs, and data-intensive applications

AI / LLM Experience

• Hands‑on experience with:
• Prompt engineering and evaluation
• RAG architectures and vector search
• LLM orchestration frameworks (LangChain, LangGraph, or similar)
• Understanding of model limitations (hallucinations, latency, cost tradeoffs, context windows)

Data & Infrastructure

• Experience with databases (SQL + NoSQL), data pipelines, and ETL processes
• Familiarity with cloud infrastructure and containerized deployments
• Understanding of system performance, observability, and scaling

Builder Mindset

• You operate well in ambiguity and move quickly from idea → implementation
• You care about whether the system actually works in production

Communication

• Able to work directly with non-technical stakeholders
• Can explain system design, tradeoffs, and limitations clearly
• Comfortable operating in client-facing environments

What Sets You Apart

• Experience deploying AI systems in production environments at scale
• Built agent-based systems or internal AI tooling used by real users
• Experience with:
• Embedding models and semantic search
• Evaluation frameworks (human-in-the-loop, automated scoring)
• Background in startups, consulting, or high-ownership environments

Why This Role

• You’ll build systems that are actually used—not prototypes
• You’ll work across the full stack of modern AI systems
• You’ll have ownership over real outcomes, not just tickets