Base Career helps you apply smarter for this job.
Key skills for this role
Astral Insights is a B2B AI company building Artemis, an operational intelligence platform for manufacturing, quality, and supply chain teams. Artemis is headless in nature and integrates with experience layers like Microsoft Teams and our web app, deploying AI agents inside our clients' operations to detect signals, diagnose root causes, and drive actions that ultimately improve the bottom line. We serve enterprise clients across life sciences, specialized manufacturing, and healthcare organizations. We operate as a lean, senior team and we hire people who want to own outcomes, not tickets.
The Forward Deployed Engineer (FDE) is our tip of the spear inside client engagements. You sit between our clients' data, our Artemis platform, and the executives who signed the deal. You configure Artemis agents to the client's domain, wire up the data pipelines that feed them, stand up the full-stack surfaces clients interact with, and you stand in front of VPs and directors to show the work and the ROI.
This role is built for someone who embraces modern AI-supported development, tried and true SWE fundamentals, and client-facing implementation. You do not need to be the world's best data engineer, full-stack developer, prompt engineer, or implementation consultant. You need to be capable across all of these domains and passionate about working closely with clients to solve meaningful problems. If the idea of being thrown a problem you have never solved before and shipping it in a week sounds exciting instead of terrifying, this might be a fit.
Configure Artemis agents for clients Own the end-to-end configuration of agents on the Artemis platform for each client deployment. Prompt engineering, context engineering, tool wiring, evaluation loops, and tuning until the agent behaves the way the client's operators expect.
Build and own the client data layer Design and ship the bronze, silver, and gold layers that feed Artemis. Ingest messy enterprise data (ERP extracts, SQL Server, flat files, APIs), clean it, model it, and land it in the structures our agents consume. You are responsible for data quality, not just data movement.
Skip the repetitive application forms
Install the Base Career Chrome Extension and autofill job applications across major job boards with your profile.
Trusted by over 500,000 job seekers on Base Career
More from this employer
Ship full-stack features end to end Contribute to the Artemis platform and its experience layers (Microsoft Teams integration and our web app) as well as the APIs that power them. Work across frontend, backend, and infrastructure. Follow real SDLC discipline (feature branches, code review, Dev → QA → UAT → Prod) and help us keep raising the bar.
Support client-facing delivery Run working sessions with client data, IT, and operations teams. Translate their requirements into sprint work. Handle the ambiguity directly rather than punting it back to the founders.
Present to executives and make the business case Walk VPs and directors through what the agents found, what actions were taken, and what it was worth. Build and deliver ROI narratives. Our champions have to be able to defend the investment to their leadership, and your deliverables are what they use.
Travel to client sites when it matters Be on the ground for kickoffs, major checkpoints, executive readouts, and go-lives. Expect roughly a dozen travel days per year across the united states.
Close the signal-to-action loop Own the outcome, not a subtask. If a signal is firing wrong, if a dashboard is stale, if an agent is hallucinating, if the data pipeline broke, it is your problem to diagnose and fix, regardless of which layer it lives in.
Use AI tools creatively and responsibly Use Claude Code, Codex, and similar tools as force multipliers. Know when to trust the output, when to verify it, and when to throw it out. We expect you to ship more than a traditional engineer, not the same amount with more help.
2 to 5+ years of engineering experience More is a plus, but we also embrace young, smart engineers looking to quickly gain experience and become a future leader in a rapidly growing enterprise software company. Across some combination of data engineering, full-stack development, and AI or ML work. You do not need depth in all three, but you need to have shipped production systems in at least one and be hungry to learn the others fast.
Strong data fundamentals Comfortable with SQL, Python, data modeling, and the bronze / silver / gold medallion pattern (or equivalent lakehouse / warehouse patterns). Hands-on experience with AWS is required (our primary stack), and experience with Microsoft Azure is a plus since we integrate with it as well.
Real prompt and context engineering chops You have built with LLMs in production, not just on weekends. You understand the difference between a prompt that works on a demo and one that works on 10,000 real records. You know how to design tool use, structure context, evaluate outputs, and debug agent behavior.
Full-stack range Comfortable shipping across frontend (React / TypeScript), backend (Python / Node / .NET), and cloud infrastructure. You understand what Dev, QA, UAT, and Prod environments are for and why they matter. You know how to read a pull request and leave a useful review.
Client-facing presence You have led calls with client teams. You have presented to executives. You can translate a technical result into a business outcome and a dollar amount without being prompted. You are comfortable being the face of the company on a customer call.
AI-native operator You use Claude Code, Codex, Cursor, or similar tools every day and have opinions about them. You see AI tools as the way to punch above your weight, not a crutch. You are excited about walking into problems you cannot yet solve and solving them anyway.
Comfort with ambiguity Early-stage startup energy. Things break. Scope changes. Clients ask for things that were not in the SOW. You handle it and keep the trains moving.
Experience in manufacturing, quality, or supply chain domains (root cause analysis, CAPA, quality investigations, S&OP, logistics).
Experience with Microsoft Fabric, Power BI, or the broader Microsoft data stack (we integrate with Azure).
Experience with Teams bot development, Microsoft Graph, or Microsoft Bot Framework.
Experience building with Anthropic, OpenAI, or AWS Bedrock model APIs at production scale.
Prior forward-deployed, solutions engineering, or implementation engineering experience at a B2B SaaS or AI company.
Bilingual (English / Spanish) is a plus given our distributed team.
Send a short note explaining what you have shipped recently, a specific example of an AI or agent system you built, and why this role fits you now. Links to code, writeups, or product demos are welcome in place of a resume.
AI-powered operational intelligence platform for supply chain teams.
Visit company websiteJobs and hiring trendsUSD 130000-180000 yearly / year
Full-time
Entry · 2+ years experience
Hybrid
Apply faster on company sites with our extension.