Overnight Python Llm Jobs (NOW HIRING)

Solstice is redefining how life sciences organizations commercialize their products. We are building a commercial engine that allows pharmaceutical marketers to take control of their content supply chain. Some reasons for why you should join us are:

• Rapid growth: Over the past year, we have been working with some of the top life sciences manufacturers as well as marketing agencies and are working with over 50+ pharma brands.

• Frontiers of technology: We're building applications and rapidly iterating technical approaches at the frontiers of AI, experimenting with LLMs and new frameworks. We have V2 of the platform currently deployed to customers but are incorporating new, advanced frameworks to our solution aggressively.

• Top-tier investors: We've raised $3.5mm+ from investors like Twelve Below, Virtue and the founders of Datavant, Commure, and Paradigm to supercharge our growth and build an elite team of engineers and operators.

Building anything great requires commitment and dedication. We're looking for someone who has the fire to prove others wrong

We're building Solstice to automate compliant, reference-backed pharma marketing. As a founding full-stack engineer, you'll own core parts of the application stack, designing APIs, background workflows, and deployment pipelines, and you'll be responsible for packaging and shipping LLM "agents" to production. Beyond development, you will be collaborating closely with co-founders Yiwen and Aris on all facets of the startup as we grow Solstice in the coming years as we ship fast, safe, and observable systems. Reach out to aris@solsticehealth.co to learn more.

• Backend services & APIs: Build and harden FastAPI services; design clean interfaces for ingestion, retrieval, annotation, and compliance checks.

• Workers & queues: Stand up a reliable background job platform with Celery + Redis (scheduling, retries, idempotency, backoff, result stores).

• Agent deployment: Package LLM/RAG agents (e.g., LangGraph/LangChain) into production service.

• Cloud & infra: Ship to AWS, manage secrets, networking, autoscaling, and cost controls.

• Integrations: Building robust, enterprise integrations with cloud platforms such as Veeva Promomats, Adobe, and Figma.

• Pipelines & files: Orchestrate file processing (PDFs, images), OCR, embedding pipelines, and metadata enrichment at scale (S3-first design).

• Data layer: Model clean schemas and access patterns for Postgres; use Redis for caching and rate-limiting; integrate vector DBs (Pinecone).

• Frontend touchpoints: Contribute to our Next.js frontend where necessary.

• Engineering chops. Relevant experience building systems & deploying enterprise-grade products

• Independent thinking. While we believe specific skills can be taught, we need someone who has the ability to make decisions and drive results on their own.

• Strong proficiency in full-stack web development technologies such as Python, FastAPI, Docker, AWS

• Experience working with LLMs such as GPT, Claude and Gemini to create LLM-based workflows, RAG Pipelines and agentic solutions. (Either formally or through projects/experimentation)

• Superb communication and collaboration skills. We believe in direct communication and willingness to provide as well as accept criticism.

• Unreal work ethic. Diamonds were not made overnight.

• Medical insurance

• Relocation support

• Opportunity to work at a high-velocity and high-energy startup

• Visa sponsorship (O-1) for internationals