Software Engineer, LLM & Automation

Basis Research Institute; New York (NY); On-site; USD 80,000 - 120,000; Full time

Job summary

A nonprofit applied AI research organization is seeking Software Engineers to develop scalable systems integrating large language models (LLMs) with operational workflows. Responsibilities include architecting automation pipelines, integrating third-party APIs, and writing production-grade code. Candidates should have experience in Julia and/or Python and strong collaboration skills. The organization offers flexible arrangements for contractors, part-time, or full-time roles.

Qualifications

• 3+ years of production-level coding in Julia and/or Python.
• Experience integrating LLMs with structured prompts and frameworks.
• Ability to handle concurrency and performance optimizations.

Responsibilities

• Architect and maintain automation pipelines using LLMs.
• Integrate data across third-party APIs into workflows.
• Write production-grade code with focus on modularity and reliability.

Skills

Programming in Julia

Programming in Python

API orchestration

Concurrency and scaling

Collaboration and communication

Tools

Docker

Kubernetes

AWS

GCP

Azure

Job description

About Basis

Basis is a nonprofit applied AI research organization with two mutually reinforcing goals.

The first is to understand and build intelligence. This entails establishing the mathematical principles of reasoning, learning, decision‑making, understanding, and explaining, and constructing software that embodies these principles.

The second is to advance society’s ability to solve intractable problems. This involves expanding the scale, complexity, and breadth of problems we can solve today and, more importantly, accelerating our ability to solve problems in the future.

To achieve these goals, we are building both a new technological foundation inspired by human reasoning, and a new type of collaborative organization that prioritizes human value.

About the Role

We’re seeking Software Engineers to develop scalable systems that integrate large language models (LLMs) with our everyday operational workflows. This role involves designing and deploying automated “pipelines” for tasks like recruiting, finance, and project management—often powered by GPT, Claude, or similar LLMs. We’re flexible on your arrangement: we’re hiring contractors, part‑time, or full‑time teammates.

Core Responsibilities

• Architect and maintain automation pipelines combining internal tools with GPT/Claude and other LLMs

• Integrate data across third‑party APIs (e.g., ATS platforms, Slack, Google) into unified, automated workflows

• Leverage structured generation (JSON schemas, function calling, etc.) to ensure robust, correct LLM outputs

• Collaborate with Ops and R&D to identify high‑impact automation opportunities

• Write production‑grade code, with emphasis on modularity, reliability, and error handling

• Deploy, scale, and optimize your solutions in a secure, cloud‑based environment

• Document solutions for both technical and non‑technical audiences, ensuring easy updates and maintenance

Qualifications and Attributes

We’re looking for individuals who:

• Have experience programming in Julia and/or Python (3+ years of production‑level coding, or equivalent)

• Understand how to integrate LLMs using structured prompts, scaffolding frameworks (LangChain‑like), or advanced text generation approaches

• Can handle concurrency, scaling, and performance optimizations in real‑world deployments

• Are comfortable with complex API orchestration: dealing with rate limits, OAuth, error retries, etc.

• Have good collaboration and communication skills, especially when gathering requirements from non‑technical staff

• Are flexible and creative problem solvers, comfortable with iterative, experimental development cycles

• Embrace data‑security best practices (e.g., handling PII, encryption, secrets management)

• Are excited to learn quickly and adapt to new developments in the LLM/AI ecosystem

Technical Skills

Preferred (not all required):

• Julia: Type‑driven or multiple‑dispatch approaches; performance tuning, HPC, or scientific computing workflows

• Python: Building microservices with FastAPI, Flask, or other frameworks; advanced concurrency (async, multiprocessing)

• LLM Tools & Frameworks: Familiarity with LangChain, open source LLM clients, or custom chain‑of‑thought integrations

• Cloud Infrastructure: Docker/Kubernetes, CI/CD pipelines, AWS/GCP/Azure deployment patterns

• Distributed Systems & Queues: Experience with concurrent processing, task queues (Celery, Sidekiq), or event‑driven systems

• Database Interaction: Ability to design schemas and queries in PostgreSQL or similar databases

• Security & Privacy: Understanding of OAuth flows, secrets management, data encryption, and role‑based access controls

Privacy Notice

By submitting your application, you grant Basis permission to use your materials for both hiring evaluation and recruitment‑related research and development purposes. Your information may be processed in different countries, including the US. You retain copyright while providing Basis a license to use these materials for the stated purposes.

Read our full Global Data Privacy Notice here.